74 resultados para "LLM"
Quantização: Rodar LLMs no Seu Computador
LLMs & TextoO que é quantização e como ela permite rodar LLMs de qualidade no seu próprio computador, com privacidade e custo zero por requisição.
Agentes de IA: O Que São e Como Pensam
LLMs & TextoAgentes de IA explicados: como um LLM deixa de só responder e passa a usar ferramentas, planejar e agir — e por que isso é mais frágil do que parece.
Mistura de Especialistas: Modelos Gigantes que Custam Pouco
LLMs & TextoO que é um modelo MoE (mixture-of-experts): como um LLM pode ter um trilhão de parâmetros e ativar só uma fração a cada token — e por que isso domina os lançamentos atuais.
LLMs: Como Funcionam os Modelos de Linguagem
LLMs & TextoEntenda de uma vez como funcionam os LLMs: a arquitetura transformer, o treinamento, por que eles alucinam, fine-tuning, RAG, quantização e agentes.
Tokens Visuais: Como um Modelo 'Lê' uma Imagem
MultimodalComo um modelo multimodal transforma uma imagem em tokens que o LLM entende: patches, projeção para o espaço de texto e por que imagens custam tantos tokens.
Aprendizado por Reforço Explicado
Robótica & RLO que é aprendizado por reforço: agente, ambiente, ação e recompensa. Como a IA aprende por tentativa e erro, do AlphaGo ao RLHF dos LLMs — e onde isso falha.
VLMs: Modelos de Visão e Linguagem
MultimodalO que é um VLM (vision-language model): como ele une um codificador de imagem a um LLM, o que consegue fazer — VQA, descrição, leitura de documentos — e seus limites.
Benchmarks Are Not Monolithic: Sample-Level Auditing and Orchestration for LLM Evaluation
LLMs & TextoarXiv:2607.28801v1 Announce Type: new Abstract: Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial variation in the demands of individual samples. We introduce a dataset-centric meta-evaluation framework that audits benchmark datasets at the sample level along five latent dimensions: 1. Cognitive and Knowledge Demands, 2. Language and Content Quality, 3. Task Properties, 4. Context, and 5. Ethics,...
Imbalanced Data Clustering via Targeted Data Augmentation Using GMM and LLM
LLMs & TextoarXiv:2607.28635v1 Announce Type: new Abstract: In Natural Language Processing (NLP), dealing with underrepresented topics is challenging, especially in unsupervised tasks where clustering might not adequately capture minority topics. To tackle this challenge, our paper presents a novel unsupervised data augmentation method that integrates Gaussian Mixture Models (GMMs) and Large Language Models (LLMs). Due to their flexibility and robustness, GMMs can detect clusters corresponding to underrepre...
The Asymmetric Effects of Knowledge Distillation on Bias in Small Language Models
LLMs & TextoarXiv:2607.28639v1 Announce Type: new Abstract: We show that knowledge distillation in small instruction-tuned language models has asymmetric effects on bias. On unambiguous tasks (BBQ-disambig), response-based distillation from a Gemma-2-9B teacher improves context-following: for the most biased baseline (SmolLM2-1.7B-Instruct), it cuts the context-overriding error rate from 44% to 24%. On ambiguous tasks (BBQ-ambig), the same distillation destroys per-item refusal calibration: 15% of items whe...
Can Zero-Shot LLMs Predict Child Malnutrition? A Fairness and Temporal Robustness Study
LLMs & TextoarXiv:2607.29082v1 Announce Type: new Abstract: Child malnutrition remains a major public health challenge in low- and middle-income countries, particularly in South Asia, where early identification of vulnerable children is critical for timely intervention and resource allocation. This study aims to evaluate the feasibility, fairness, and temporal robustness of using a pretrained large language model (LLM) in a zero-shot setting for child stunting prediction using population health survey data....
TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text
LLMs & TextoarXiv:2607.28862v1 Announce Type: new Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage. Unlearnable examples (UEs) offer a promising defense by introducing carefully designed perturbations into data such that models trained on them exhibit degraded utility. However, existing methods for text protection are pri...
NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability
LLMs & TextoarXiv:2607.28942v1 Announce Type: new Abstract: Recently Large Language Models (LLMs) have been increasingly deployed as autonomous agents in applications such as self-reflection, retrieval-augmented generation, and scientific discovery. In these settings, agents must act based on limited observations rather than full environmental states, leading to partial observability. This introduces several key challenges: belief state inference, task objective misalignment, and planning under uncertainty....
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
LLMs & TextoarXiv:2607.28956v1 Announce Type: new Abstract: Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success criteria. Real-world deployments often require Long-Term Coherence, the capacity to preserve purposeful behavior across extended horizons while adapting decisions to accumulated evidence. Evaluating this capacity requires a persistent environment in which actions constrain future choices, feedback arrive...
Benchmarks Are Not Validation: A System-Level View of Financial LLM Applications
LLMs & TextoarXiv:2607.28840v1 Announce Type: new Abstract: Large language models are increasingly deployed in financial applications that combine retrieval, proprietary data, tool use, orchestration logic, monitoring, and human escalation. Yet evaluation often remains model-centric: benchmark scores, task accuracy, or one-off qualitative reviews are treated as evidence of readiness. In financial settings, this is insufficient. We take the position that financial LLM systems should not be approved for produ...
D-VLC: Decentralized Vision-Language Collaboration for Heterogeneous Embodied Multi-Robot Systems in Unknown Environments
Robótica & RLarXiv:2607.29009v1 Announce Type: new Abstract: Multi-robot systems, particularly heterogeneous robot swarms, can improve the efficiency of complex task execution through parallel collaboration and complementary capabilities. However, conventional rule-based methods rely on predefined task models and specialized decision making programs, making it difficult to understand complex semantic instructions and coordinate heterogeneous robots. LLMs introduce strong language understanding and task reaso...
Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds
LLMs & TextoarXiv:2607.28908v1 Announce Type: new Abstract: Reflection, the ability to revisit and revise prior reasoning, is central to how humans improve their answers. Large language models (LLMs) are increasingly prompted to "reflect," yet whether this resembles human revision remains unclear. We introduce the Human-LLM Reflection Framework (HRF), a controlled two-pass protocol comparing human and LLM revision under identical conditions across self-, peer-, and cross-agent settings. Using an information...
How Hard Does It Think? Analyzing Step-Aware Reasoning Energy in LLM Chain-of-Thought Trajectories
LLMs & TextoarXiv:2607.28674v1 Announce Type: new Abstract: Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpretability methods rely on output-level signals or collapse processing depth into a single trajectory-level scalar, leaving step-wise effort opaque. We propose Step-Aware Reasoning Energy (SARE), a geometric framework that quantifies effort at the granularity of individual CoT steps via Centered Kern...
MirrorCraft: Paired Evaluation under Hidden Rule Changes in Minecraft
LLMs & TextoarXiv:2607.29218v1 Announce Type: new Abstract: With the prosperity of the large language models (LLMs), it has become an interesting topic: how do LLM-based agents work in Minecraft? Unfortunately, most existing benchmarks evaluate them under fixed game mechanics. High performance in these settings does not show whether an agent can continue making progress when familiar recipes, drops, and other rules change. In this paper, we introduce MirrorCraft, a paired benchmark for evaluating agents und...
Faster but Different: Diagnosing and Controlling Content Drift in Accelerated Multimodal Diffusion Language Models
LLMs & TextoarXiv:2607.29079v1 Announce Type: new Abstract: Training-free acceleration makes diffusion-based multimodal large language models (dMLLMs) more deployable, but it may silently change generated content. We study this serving-time consistency problem on 300 real images, comparing Fast-dLLM outputs with the same model's unaccelerated outputs. Across the mild parallelism induced in our long-form setting (1.05--1.25 committed tokens per step), confidence-threshold tuning changes decoding behavior but...
Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
LLMs & TextoarXiv:2607.28661v1 Announce Type: new Abstract: Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding numerical precision and multi-step logic over long contexts, is an ideal testbed. Existing benchmarks fail to capture real-world industrial complexity, predominantly relying on multiple-choice questions or single-hop QA over cropped tables while ignoring intricate cross-statement dynamics and tempor...
Self-Supervised Skill Optimization
LLMs & TextoarXiv:2607.28777v1 Announce Type: new Abstract: Agent skills provide frozen large language model (LLM) agents with reusable procedural guidance, and recent work shows that such skills can be optimized with ground-truth (GT) feedback. Many applications, however, lack GT labels, task scores, rewards, or reliable task-specific evaluators. We therefore introduce Self-Supervised Skill Optimization (SSO), a comparative framework that learns a reusable skill from unlabeled task instances alone. At each...
SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs
LLMs & TextoarXiv:2607.28969v1 Announce Type: new Abstract: Although Large Language Models (LLMs) have demonstrated promising safety performance, extending them to Multimodal Large Language Models (MLLMs) exposes a significant gap between expanded multimodal capabilities and existing safety mechanisms. Current defenses remain predominantly confined to specific modal settings, thereby limiting their robustness against broader cross-modal threats. To bridge this gap, we introduce SafeNexus, a cross-modal safe...
Overcoming the Weakest-Link Effect in LLM-Driven Program Optimization via Heterogeneous Edit Recombination
LLMs & TextoarXiv:2607.28947v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to solve complex problems by searching over program space, offering a general paradigm for scientific problems that can be naturally represented and solved as programs. Despite recent progress, identifying effective optimization directions for a candidate program remains challenging. By analogy with automatic differentiation, existing methods typically guide the search using a textual ``gradient'':...
TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs
LLMs & TextoarXiv:2607.28640v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) should generate consistent responses given semantically equivalent inputs across modalities. However, we observe a systematic discrepancy in model predictions under such cross-modal variations. Specifically, we define the modality gap as the difference in model performance under semantically equivalent textual and multimodal inputs. We introduce TokenSwap, a method that constructs such inputs by replacing te...
TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter
LLMs & TextoarXiv:2607.28657v1 Announce Type: new Abstract: Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users. This work addresses the challenge by introducing a Task-Aware Prompt Rewriter (TAPR), a model that reformulates user prompts into task-optimized prompts with the explicit goal of improving downstream LLM performance. We train TAPR using reinforcement learning with Group Relative Policy Optimization (GRPO)...
TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking
LLMs & TextoarXiv:2607.28680v1 Announce Type: new Abstract: Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on data preprocessing pipelines that retain either compact or extensive table content as contextual evidence, and then formulate entity linking as a language generation task for instruction-tuned models; recent systems further incorporate explicit reasoning to disambiguate challenging mentions. Howeve...
LLM Framework for Discovering Major Mathematical Conjectures: AI's Quest for the Next Riemann Hypothesis
LLMs & TextoarXiv:2607.28632v1 Announce Type: new Abstract: Major mathematical conjectures still depend heavily on expert intuition, so a unified method for the systematic generation and validation of conjectures with substantial mathematical potential remains unavailable. We present a three stage pipeline for major conjecture discovery, with region search from explicit local evidence modules, reflective validation for foundationality, novelty, and potential significance, and formal validation in Lean 4 and...
Semantics of Subterfuge: Benchmarking Legal Deception Detection Against General-domain State-of-the-Art
LLMs & TextoarXiv:2607.29066v1 Announce Type: new Abstract: Deception detection has critical implications for legal proceedings, law enforcement, and online security. Although human judgment is limited in accuracy and scalability, Natural Language Processing (NLP) offers a data-driven alternative. We present a survey and comparative analysis of NLP-based Automatic Deception Detection (ADD) focusing on the legal domain, reviewing the evolution from feature-based machine learning to Large Language Model (LLM)...
Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support
LLMs & TextoarXiv:2607.28677v1 Announce Type: new Abstract: LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning. These developments have accelerated the use of LLMs for symptom assessment and clinical decision support in diagnostic and treatment guidance, administrative documentation, and rules-based alert enhancement. This Perspective concerns the most consequential of these applications: the autonomous triage of self-presenting, undifferentiated ...
Can LLMs Really Understand Item Difficulty Levels? Implications for Automated Item Generation Using LLMs
LLMs & TextoarXiv:2607.28634v1 Announce Type: new Abstract: The estimation of item difficulty plays a key role in both formative assessment and large-scale high-stakes summative assessments. This study explores how large language models (LLMs) perform in predicting item difficulty levels using items from a large-scale Reading and Writing test. The study investigated various prompting strategies and parameter settings across multiple LLMs. LLM performance was compared with encoder-only language models and fe...
CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning
LLMs & TextoarXiv:2607.29172v1 Announce Type: new Abstract: While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-source, limiting downstream users' ability to adapt them to new tasks, embodiments, and deployment settings. Following the LLM community, an emerging access paradigm for closed-weight robot foundation models is the managed supervised fine-tuning (SFT) API, where users submit training data and receive a tun...
Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL
LLMs & TextoarXiv:2607.29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases. As a result, multi-reward reinforcement learning (RL) has become an increasingly important problem for LLMs, where each reward captures a different aspect of desired behavior. However, optimizing with multiple rewards suffers from a more severe alignment tax issue, where different optimization objective...
CAGE: Certified Authorization under Typed-Return Uncertainty for Tool-Using Agents
LLMs & TextoarXiv:2607.29190v1 Announce Type: new Abstract: Tool-using LLM agents act on typed tool returns, records pairing provenance and categorical fields with numerical values. Runtime permission gates generally authorize the observed return and action, leaving the decision unprotected against small errors in how the return was bound to its source. We ask whether a candidate action stays authorized over a declared neighborhood of plausible correctly bound returns: one admissible binding fault plus boun...
Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration
LLMs & TextoarXiv:2607.29087v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in enterprise settings, yet individual models remain bounded by model-specific capability limitations. These heterogeneous boundaries pose a deployment challenge, but also create an opportunity: strategically coordinating multiple LLMs may unlock collective intelligence exceeding any single model. Existing approaches fix how models are combined in advance, overlooking the dynamic, state-depende...
CAER: Conflict-Aware Evidence Routing with Dual Prefix Experts for Multimodal Large Language Models
LLMs & TextoarXiv:2607.28991v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in multimodal understanding and generation. However, when textual inputs conflict with visual evidence, they still suffer from hallucinations and produce responses inconsistent with visual content. Existing approaches mainly rely on decoding strategies, additional training, verification methods, or prompting techniques, but often lack fine-grained conflict localizati...
Learning Stateful Predictive Knowledge From Experience
LLMs & TextoarXiv:2607.28638v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights. Viewed through the lens of predictive knowledge, we argue that this approach operates on episodic hindsight rather than predictive foresight, yielding brittle, path-dependent heuristics. To address this, we propose Stateful Knowledge Learning (SKL). SKL shifts the agent's focus from trajectory-level summar...
Token-Level Diagnosis of Sycophancy in LLMs with Attribution-Guided Steering
LLMs & TextoarXiv:2607.28906v1 Announce Type: new Abstract: Sycophancy refers to the tendency for large language models (LLMs) to match user beliefs at the cost of factual correctness, thereby undermining model reliability. Prior work on evaluating sycophancy in LLMs aims to assess whether a model's output matches an authority's claim, but cannot reveal which part of the prompt drives this sycophantic behavior. To bridge this gap, we investigate the relationship of sycophantic responses with an authority's ...
Topology-Aware Data Movement for Disaggregated GPU Inference
LLMs & TextoarXiv:2607.28633v1 Announce Type: new Abstract: Disaggregated LLM inference creates a datacenter networking problem that no existing system solves correctly. When prefill and decode run on separate GPU pools, the KV cache must be transferred between them. For a 70B model this is 2.6 GB per request, exceeding 100 GB/s aggregate at production scale. Yet DistServe, Splitwise, and Mooncake all use uniform RDMA, ignoring that bandwidth between two GPUs varies by 72x depending on their physical relati...
An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks
Robótica & RLarXiv:2607.28854v1 Announce Type: new Abstract: Discrete choice modeling is a common tool used for preference elicitation during policy-making, but this is typically done through parametric models. Machine learning can push the boundaries of discrete choice modeling for policy-based preference elicitation by adopting a data-driven approach or learning individual preferences. However, there is limited knowledge of how well machine learning methods can estimate individual discrete choice rules und...
Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges
LLMs & TextoarXiv:2607.28636v1 Announce Type: new Abstract: LLMs increasingly serve as automated judges, but their judgments remain vulnerable to cognitive biases. Existing mitigations mostly rely on prompt-driven debiasing, which is brittle across bias types, or human evaluation, which does not scale. We study \emph{Chain-of-Models} (CoM), an automated audit pipeline in which a second model inspects the first model's reasoning trace before producing the final judgment. The key design question is whether th...
HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation
LLMs & TextoarXiv:2607.29600v1 Announce Type: new Abstract: Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has emerged: the robot queries a multimodal LLM to understand its observations and plan the next action. However, long-horizon navigation based on either image streams or dense map inevitably introduces a growing memory and reasoning bottleneck. We present HAM-VLN, a decision-coupled, agent-authored memory...
Rolling With Resistance: Preference-Optimized LLM Counselors Can Trade Goal Persistence for Relational Attunement in Motivational Interviewing
LLMs & TextoarXiv:2607.28814v1 Announce Type: new Abstract: In Motivational Interviewing (MI), a client's sustain talk (arguments for the status quo) calls for the counselor to roll with resistance, a move that can fail in two opposite ways: capitulation (abandoning the change agenda to preserve rapport) or confrontation (arguing or directing, overriding the client's autonomy). We introduce a two-axis evaluation of counselor responses, anchored in the Motivational Interviewing Treatment Integrity (MITI) cod...
FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation
LLMs & TextoarXiv:2607.28934v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly involved in the distribution of scarce resources, raising concerns about biased allocations based on characteristics like race and gender. Recent LLM audits have produced inconsistent results, however, finding evidence of both positive and negative discrimination towards women and ethnic minorities, even for the same models. We show that this disagreement can arise from differences in audit format and i...
The Formalism Trap: Are LLM-as-a-Judge Evaluators Blinded by Consensus Mimicry under Social Load?
LLMs & TextoarXiv:2607.28641v1 Announce Type: new Abstract: We introduce the \textit{Agentic Formalism Trap} and the Evaluative Dissonance Index ($D_E$), quantifying how LLM-as-a-Judge systems conflate structural proceduralism with semantic truth under adversarial load. Analyzing 22,500 trajectories across 3 domains (GAIA, SWE-bench, Multi-Challenge), we extract a semantic taxonomy of hallucination maneuvers, validated via deterministic lexical grounding ($p < 10^{-120}$). A logistic meta-evaluator isolates...
Guarantees on Dynamical System Distinguishability for LLM Token Generation
LLMs & TextoarXiv:2607.28667v1 Announce Type: new Abstract: Recent work has shown that classifying large language models (LLMs)' responses can be distinguished by modeling token embeddings as trajectories of a black-box dynamical system (DS) and comparing prediction residuals of two DSs. Despite the empirical success of this dynamical approach, a theoretical understanding of why it works, how well it scales as a function of the token sequence, and when it transfers across embedding models remains lacking. W...
BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning
LLMs & TextoarXiv:2607.28966v1 Announce Type: new Abstract: Large language models often improve task performance by generating long reasoning traces, but the resulting computation is frequently wasted on redundant verification and revision. Existing probe-based early-exit approaches mainly inspect explicit self-doubt expressions, leaving many earlier termination opportunities undetected. Expanding inspection to ordinary reasoning boundaries improves coverage, but also exposes highly diverse intermediate sta...
Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models
LLMs & TextoarXiv:2607.28979v1 Announce Type: new Abstract: Heterogeneous Large Language Model (LLM) systems increasingly rely on shared contexts, retrieved evidence, and multi-agent dialogue histories, yet their internal key-value (KV) caches remain model-specific and cannot be reused across architectures. Consequently, each model must repeatedly prefill or store caches for the same context, limiting the scalability of multi-model reasoning and long-context generation. We propose Mixture-of-Translators(MoT...
SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition
LLMs & TextoarXiv:2607.28692v1 Announce Type: new Abstract: Large language model (LLM) agents have been increasingly adopted in scientific research for organizing and invoking specialized computational tools. However, their reliance on predefined tool spaces with static semantics limits their applicability to open-world scientific workflows, where tool requirements, capabilities, and boundaries evolve dynamically. To this end, we propose SciToolAgent-Evo, an ontology-aware self-evolving agent for open-world...
OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systems
LLMs & TextoarXiv:2607.28629v1 Announce Type: new Abstract: The rapid transition from reactive large language models (LLMs) to persistent, action-capable systems has exposed critical gaps in the architectural understanding of Agentic AI, particularly in separating inference, orchestration, and execution layers for autonomous AI agents. Despite recent advances, unified frameworks for designing and evaluating full-stack agentic systems remain limited. This paper presents a comprehensive, layered architecture ...
Onton Releases Ontology 1: A Neurosymbolic Search Model That is 2.7x More Accurate than the World’s Best E-commerce Search Engines
Dados & EmbeddingsOnton, a San Francisco-based search and discovery company, has released Ontology 1, a neurosymbolic model for complex, conversational, multimodal product search. On a 90-query benchmark scored by three independent LLM judges, Ontology 1 reached a mean precision@10 of 0.630, against 0.543 for Google Shopping and 0.469 for Amazon. It did this while indexing roughly 1% […] The post Onton Releases Ontology 1: A Neurosymbolic Search Model That is 2.7x More Accurate than the World’s Best E-commerc...
Thinking Machines Lab Releases Inkling-Small: A 276B Total, 12B Active Open Weights Multimodal MoE Model
LLMs & TextoInkling-Small matches Inkling at a quarter the size, and its NVFP4 checkpoint runs on one NVIDIA B300 GPU The post Thinking Machines Lab Releases Inkling-Small: A 276B Total, 12B Active Open Weights Multimodal MoE Model appeared first on MarkTechPost .
NVIDIA AI Releases Molt: A PyTorch-Native Agentic Reinforcement Learning Framework
LLMs & TextoAgentic RL research is constant algorithm modification, and in mainstream frameworks every change threads through trainer, distributed backend, and rollout glue. NVIDIA's Molt targets that cost with about 8.6K lines of RL code, composing Ray, vLLM, and NeMo AutoModel around one asynchronous loop. The agent stays ordinary Python, trajectories stay token-exact, and throughput comes out statistically comparable to a Megatron-based stack. The post NVIDIA AI Releases Molt: A PyTorch-Native Agentic Re...
YouTuber Hank Green says his AI usage is ‘not healthy’
LLMs & TextoGreen offered a remarkable apology, saying that "the level of dopamine that I've been getting from interacting with LLMs ... is not healthy for me or good for the world."
AMD Releases Instella-MoE-16B-A3B: A Fully Open Mixture-of-Experts LLM With 2.8B Active Parameters Trained On Instinct GPUs
LLMs & TextoAMD released Instella-MoE-16B-A3B, a fully open Mixture-of-Experts language model trained from scratch on Instinct MI300X and MI325X GPUs. It holds 16B total parameters but activates only 2.8B per token, using Gated MLA and FarSkip-Collective. AMD published weights from every training stage, plus data mixtures, configs, and inference code. The post AMD Releases Instella-MoE-16B-A3B: A Fully Open Mixture-of-Experts LLM With 2.8B Active Parameters Trained On Instinct GPUs appeared first on MarkTec...
Sam Altman is still making the case for parenting via ChatGPT
LLMs & TextoThis isn’t the first time a tech CEO has promised that AI can shield users — and specifically users’ morning commutes — from the messiness and inefficiency of human experience.
Supabase Releases Evals: an Open Source Benchmark That Scores Claude Code, Codex and OpenCode on Real Supabase Tasks
LLMs & TextoSupabase has open sourced supabase/evals, an Apache-2.0 benchmark and framework that runs coding agents including Claude Code, Codex and OpenCode against real Supabase tasks — building schemas, debugging Edge Functions, fixing RLS policies — inside containerized stacks, then scores them with deterministic checks and LLM-as-a-judge. The post Supabase Releases Evals: an Open Source Benchmark That Scores Claude Code, Codex and OpenCode on Real Supabase Tasks appeared first on MarkTechPost .
JetBrains Open-Sources KotlinLLM: Smart Macros That Generate Kotlin Source Code at Runtime and Hot-Reload It Through JDI
Robótica & RLJetBrains Research has open-sourced KotlinLLM under the Apache License 2.0. The IntelliJ IDEA plugin prototype adds Smart macros, asLlm and mockLlm, whose bodies are generated Kotlin source rather than live model calls. The plugin captures runtime values through JDI, asks an LLM agent for a narrow code update, compiles it, and redefines the loaded class. Covered scenarios then run as plain Kotlin with no further inference call. On an adapted Spring Petclinic project, 24 of 24 scenarios completed...
PolyAI Releases Dialog-RSN-1: An Audio-Native Dialog Model That Fuses Turn-Taking, Speech Recognition, Function Calling, And Response
Áudio & VozPolyAI has introduced Dialog-RSN-1, a dialog model that perceives caller audio directly instead of reading an ASR transcript. It fuses turn-taking, speech recognition, function calling, and response generation into a single audio-native model, keeps TTS separate so the output voice stays controllable, and runs as a request-based LLM rather than an always-on stream. PolyAI reports sub-300ms responses in live deployments. The post PolyAI Releases Dialog-RSN-1: An Audio-Native Dialog Model That Fus...
BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences
LLMs & TextoarXiv:2607.27366v1 Announce Type: new Abstract: While data synthesis for large language models (LLMs) is prevalent, it primarily targets domains with verifiable answers, overlooking open-ended humanities and social sciences (HSS), where nuanced quality judgments matter more than objective correctness. This makes preference alignment a natural paradigm for broad HSS tasks. Yet existing methods are either costly or not tailored to broad HSS disciplines. We thus propose BridgeAlign, among the first...
AlphaSchema: Exploring the Space of Trading Semantics for LLM-Based Alpha Mining
LLMs & TextoarXiv:2607.26642v1 Announce Type: new Abstract: Automated alpha mining has increasingly adopted large language model (LLM) agents for factor generation and iterative discovery. However, existing LLM-based systems often delegate both factor construction and search decisions to the agent itself, without an explicit exploration space or a principled mechanism for navigating that space. As a result, exploration remains largely implicit and difficult to control or optimize systematically. We introduc...
HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs
LLMs & TextoarXiv:2607.27379v1 Announce Type: new Abstract: High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. Data synthesis is a viable alternative and succeeds on closed tasks, yet the humanities and social sciences (HSS) are overlooked, and their open-ended nature makes synthesis challenging. Moving beyond prior capability-centric, fragmented attempts, we adopt a subject-centric paradigm, define the first HSS domain system covering 14 mainstream fields, a...
Exploring Structures in Physics Problems: Can AI Agents Discover Statistical Mechanical Mappings?
LLMs & TextoarXiv:2607.26367v1 Announce Type: new Abstract: An important skill in theoretical physics is to recognize when a new problem can be transformed into a known model. We study this skill as an AI-agent task: can LLM-based agents discover statistical mechanical mappings from a raw partition function to a tractable representation? To probe this question, we introduce StatMechBench-v0, a benchmark of six Ising-type problems covering transfer-matrix methods, gauge-removable disorder, and planar/Pfaffia...
GoGoTB: Agentic RTL Verification with Specification-Grounded Coverage Closure
LLMs & TextoarXiv:2607.26181v1 Announce Type: new Abstract: Functional verification dominates integrated circuit (IC) front-end engineering effort, and a single missed bug that escapes to silicon can trigger a costly respin. Recent large language models (LLMs) offer new opportunities to automate this process, yet existing LLM-based approaches generate each component through independent single-turn calls with no shared context, leaving interface mismatches undetected and reported coverage disconnected from s...
DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation
LLMs & TextoarXiv:2607.27614v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have led sign language translation (SLT), the task of converting sign-language videos into spoken-language text, to increasingly adopt LLMs as textual backbones. However, despite their strong language modeling capabilities, existing LLM-based SLT methods often undermine rather than exploit this language prior, producing disfluent translations, a failure we term language-prior degradation. Meanwhile, e...
Benchmarking LLM Competence on Logical Inference over Probability Operators
LLMs & TextoarXiv:2607.27405v1 Announce Type: new Abstract: Both expressions of uncertainty and inferences are ubiquitous in natural language, and valid inferences over natural-language expressions of uncertainty are necessary for not only everyday conversations but also for high-stakes domains such as medicine and law. While large language models are increasingly evaluated on logical reasoning tasks, disentangling principled, symbolic reasoning from clever surface-level pattern matching is fraught with dif...
PanDent: Toward Comprehensive Tooth-Level Structure-Language Consistency in Dental Radiology
LLMs & TextoarXiv:2607.27378v1 Announce Type: new Abstract: Accurate evaluation of multimodal large language models (MLLMs) in dental panoramic radiography (orthopantomogram, OPG) is limited by the lack of fine-grained, clinically reliable benchmarks that reflect expert interpretation. This work introduces PanDent, a large-scale, clinically grounded OPG benchmark built upon fine-grained, expert-validated tooth-level annotations. The dataset comprises 9,524 high-quality OPGs, each associated with comprehensi...
ChronoMem: Version Control and Semantic Rollback for Large Language Model Agent Memory
LLMs & TextoarXiv:2607.27773v1 Announce Type: new Abstract: LLM agents increasingly rely on long-term memory to support multi-session interaction and personalization. However, existing agent memory systems are designed around forward-only evolution, continuously accumulating, consolidating, and overwriting knowledge, with no principled mechanism to inspect, version, or revert prior states. This makes agents brittle under corrections, concept drift, and memory corruption, particularly after they have already...
MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models
LLMs & TextoarXiv:2607.27637v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or shifted contexts. A reliable MLLM should refuse truly out-of-context (OOC) questions with subject-level context shifts while still answering shifted in-context (Shifted IC) questions with non-subject context shifts. Existing benchmarks mainly target OOC or visually unanswerable questions, but overlook...
GuideSkill: Evolving Executable LLM Agent Skills for Guideline-Grounded Clinical Reasoning
LLMs & TextoarXiv:2607.26160v1 Announce Type: new Abstract: Clinical practice guidelines (CPGs) encode diagnostic criteria, but LLM systems typically retrieve guideline text or absorb it through training rather than execute its rules. We introduce GuideSkill, an external reasoning layer that compiles disease-specific criteria into executable functions returning ordinal diagnostic-support scores. GuideSkill-Zero is initialized from guidelines, while GuideSkill-Evo uses case--diagnosis pairs to refine covered...
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
LLMs & TextoarXiv:2607.27155v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding. The benchmark comprises 100 tasks derived from office-suite requests pr...
AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolution
LLMs & TextoarXiv:2607.26661v1 Announce Type: new Abstract: Ascend C operator optimization is critical for NPU (Neural Processing Unit) inference performance but requires deep hardware expertise.While large language models (LLMs) have shown promise in automated CUDA kernel generation, the fundamentally different programming model of Ascend C introduces unique challenges that remain unexplored. In this paper, we propose AgenticCANN, a knowledge-augmented agentic evolution framework specifically tailored for ...
Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models
LLMs & TextoarXiv:2607.27512v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in multi-agent environments. However, the processes by which beliefs form and propagate among interacting LLMs remain poorly understood. We introduce CoevolveSim, a framework for studying belief diffusion within networked LLM populations. CoevolveSim allows us to isolate and study three factors: domain specialization, social-role assignment, and social network structure. Within this framework, ...
LLMs & Texto
LLMs & TextoModelos de linguagem, agentes, raciocínio e o estado da arte em texto.