Tema

LLMs

3024documentos

265últimos 7 días

Do LLMs Act on What They Know? From Partner Representations to Cooperative Actions

Cooperation with unfamiliar partners requires adapting to communication conventions that are not known in advance. We study this problem in a controlled Hanabi-derived environment with scripted hint generation, LLM-controlled receiving decisions, and frozen model weights. Across eight LLMs, linear probes recover intent conventions substantially more accurately than target conventions, yet receiving choices do not consistently agree with the sender's convention. We compare probe-predicted and ground-truth conventions presented either as general rules or as externally computed action recommendations. Rule statements yield modest and model-dependent changes in cooperation, whereas action translation produces larger gains on average. In a Qwen3-8B case study, matched-state statement reversals reveal much greater sensitivity to action recommendations than to rule statements. Activation transfers from oracle-action and non-oracle hint-restatement donors improve intent accuracy on both action classes, but the tested alternatives do not reliably reproduce these benefits. Together, these results distinguish convention decodability, sensitivity to convention information, and cooperative performance, and highlight limitations in turning available partner information into receiving decisions.

arXiv AI Papersel mes pasado

Enhancing Diffusion Language Models with Autoregressive Post-Training Weights

Diffusion language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) language models, offering flexible token-update orders and parallel decoding. Recent dLLMs are often initialized from pretrained AR models before diffusion conversion in order to inherit their learned representations. After the conversion, however, they typically ignore the extensive post-training ecosystem of their AR ancestors. In this work, we show that these existing AR post-training weight updates can instead be effectively recycled to enhance diffusion models. Despite the changes by AR-to-diffusion conversion, directly adding an AR post-training weight update to a diffusion base model remains effective, bringing its performance close to that achieved by direct diffusion post-training. Notably, AR and diffusion post-training updates are nearly orthogonal in weight space, yet induce substantially more aligned representation changes in the diffusion model. Their distinct updates are also complementary: composing their weights can retain gains from both regimes and further improve the post-trained diffusion model. Based on these findings, we propose A2D, a simple training-free framework for enhancing diffusion models with existing AR post-training resources. A2D can transfer capabilities from AR post-trained models to diffusion base models, and further improve already post-trained diffusion models by composing AR and diffusion post-training updates. Across various dLLMs, including Dream, DreamReasoner, DiffuCoder, Dream-Coder, Nemotron-Labs-Diffusion, and DiffusionGemma, A2D reliably improves instruction following, mathematical reasoning, and coding with both supervised fine-tuning and reinforcement learning updates, without additional training, or inference-time computation.

arXiv AI Papersel mes pasado

ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications

Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observed capability gaps. Such investigation requires an expressive task format and an on-demand construction process: information-rich charts make chart question answering (Chart QA) suitable for probing coupled perception and reasoning. Automated Chart QA construction is intended to shorten the benchmark-development cycle by turning identified gaps into targeted samples on demand. Current methods, however, commonly separate target guidance from scratch generation: target-guided systems often require prepared data, charts, or templates, while scratch-generation systems primarily ensure artifact validity, without explicitly controlling whether newly synthesized requirements and content remain aligned with an externally specified diagnostic target. We introduce ChartBmkAgent, which turns an identified capability gap into targeted diagnostic evidence by constructing complete Chart QA samples from sparse error-taxonomy specifications. Throughout construction, a central harness governs specialized agents, requires stage-specific evidence of alignment with the original error category, and records the basis for each acceptance decision. On 300 taxonomy-wide samples, MLLM accuracies ranged from 32.7% to 84.3% with distinct category profiles, showing that generated samples reveal capability differences. Across three source-model comparisons, targeted follow-ups scored 50.0% versus 82.2% on matched controls (p=8.9610^{-6}); all six cross-model comparisons had the same direction, demonstrating targeted validation and diagnostic-data generation. Multiple evaluator models assessed whether each sample tested its specified error category; 86.4% met this criterion, providing empirical evidence of target preservation.

arXiv AI Papersel mes pasado

Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems

Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and failure diagnosis regulate or inspect recorded information; they do not by themselves establish whether it is sufficient to judge task duties. We define execution consistency through duties governing state use, information handoffs, and final-state agreement, with explicit evidence conditions for judging fulfillment. Our core claim is that identical retained records can correspond to compliant and violating executions under the same task rule. Controlled removal of evidence such as receipt, action dependence, or response validity leaves 82.4% of opposite-label pairs indistinguishable; restoration separates 97.9% of the merged pairs. Natural-log annotations identify the defined violations in actual executions. However, existing logs do not always explicitly represent the execution relationships needed for these judgments. To assess the definition's practical value, we use CAVERT, a framework for consistency diagnosis and recovery, to extract supported relationships from logs and apply these criteria. It consistently outperforms contract-prompted LLM and rule-based baselines in diagnosis across all 12 benchmark-executor settings. Under the same gate and executor limits, it also outperforms rule-guided recovery in all four evaluated environments. These findings identify execution evidence that agent-memory and execution interfaces should preserve for reliable judgment.

arXiv AI Papersel mes pasado

Surviving the Router: Optimizing Skill Injections for Retrieval and Execution

AI agents increasingly rely on modular third-party "skills" that are dynamically selected by skill routers to execute complex tasks. While recent studies highlight the threat of prompt injections embedded in these skills, existing evaluations often assume settings where the malicious skill is already selected for execution. We show that this assumption can substantially overestimate attack success. In realistic multi-skill environments, injected skills must first compete for retrieval, reducing the effective attack success rate (ASR) of existing injections by 87-97%. To address this limitation, we introduce CORSA (Cluster Optimization for Router-Aware Skill Attacks), a router-aware attack that optimizes skill injections for both retrieval and execution across clusters of related tasks. We evaluate skill injection attacks under router-managed multi-skill settings by extending the benchmark introduced by SkillRouter with eight malicious payload categories. CORSA uses successive optimization stages to first improve retrieval and then optimize end-to-end attack success, while we evaluate user utility and injection naturalism separately. Our experiments show that CORSA substantially improves both retrieval and end-to-end attack success over existing skill injections while preserving user utility, and that the resulting attacks transfer across different router architectures and LLM backbones.

arXiv AI Papersel mes pasado

Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing

Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advanced Text-to-SPARQL, yet on unfamiliar graphs they often generate valid queries that misrepresent the populated data model. QRAKEN is a training-free, ontology-agnostic neurosymbolic pipeline grounding generation in empirical graph evidence rather than schema expectations. An offline distiller produces TTQL, a compact description of populated multi-hop patterns, conditional frequencies and path-conditioned literal examples, plus a class-property co-occurrence matrix. Online, TTQL guides the LLM, while deterministic syntax, vocabulary and data-model checks provide diagnostics for iterative refinement. On CK25 (First International Text2SPARQL Challenge), under matched-condition recomputation on a QLever snapshot, QRAKEN achieves strict F1 of 0.643 0.026 with GPT-4.1 mini and 0.652 0.012 with GPT-5.4: relative gains of 30% and 32% over the strongest recomputed participant, outperforming systems using the same base model family. Ablations identify TTQL patterns as the dominant driver (+0.31 strict F1 over a shape-only baseline); the refinement loop provides a cheap safety net, rejecting triple patterns unsupported by the co-occurrence matrix. Compared with auto-derived SHACL, TTQL yields 64% higher strict F1, supporting the value of empirical patterns beyond schema exposure. With two local 35B 4-bit open-weight models at zero marginal cost, the same pipeline matches the strongest recomputed participant, and TTQL advantages over shape-only and SHACL baselines persist. Results on a single, relatively small benchmark provide an initial empirical signal; monolithic TTQL injection on very open cross-domain graphs remains the main limitation.

arXiv AI Papersel mes pasado

SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data Synthesis

Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-quality, expert-annotated training data. This challenge is exacerbated by stringent privacy requirements and the impracticality of utilizing large open-source corpora or proprietary cloud APIs within resource-limited clinical settings. To address these obstacles, we introduce SAGE (Semantic Anchor-Guided Evolution), a novel data synthesis framework that enables small, locally deployed models to generate high-quality medical training data. SAGE leverages lightweight, publicly available taxonomies such as MeSH as semantic anchors, imposing a structured prior to effectively guide and ground the data generation process. At its core, SAGE iteratively interleaves atomic (individual concept-based) and associative (relation-based) synthesis, bootstrapping training data from minimal seeds. This approach eliminates the need for large collections of medical documents or reliance on external APIs, providing a practical solution for on-premises data creation. Extensive experiments across multiple medical question-answering benchmarks demonstrate that models fine-tuned with SAGE-synthesized data consistently outperform those trained using self-derived or conventional document-based paradigms, highlighting tangible improvements in data efficiency and resource utilization for medical LLM development. Code is available at https://github.com/DIaacKr/SAGE.

arXiv AI Papersel mes pasado

Explainable Rule Mining of IPv6 Extension-Header Presence Patterns from Paired-Vantage Captures

IPv6 extension headers (EHs), such as fragmentation, segment routing, and in-situ telemetry, are operationally important yetwidely dropped in transit, and characterising their behaviour from packet captures is a recurring measurement problem. We ask whetheran explainable miner can recover human-readable rules of EH behaviour, and we contribute two reusable tools: a negative-control protocol that diagnoses whether a mined "temporal" network rule reflects genuine cross-packet dynamics or mere within-packetco-occurrence, and a sender-conditioned, per-family EH-retention measurement. Applying an interpretable temporal-logic rule miner to the JAMES paired-vantage dataset, we recover a portable Fragment-EH rule that the protocol reveals to be a within-packet,near-definitional co-occurrence rather than a temporal pattern, so the temporal-logic machinery does no work for this dominant rule;the retention measurement independently recovers the expected within-window ordering of EH observability. Our main result istherefore an honest, controlled negative finding, corroborated by executed decision-tree and large-language-model baselines: on theevaluated JAMES traces network-temporal structure does not carry the dominant Fragment-EH signal, and we supply the controls thatestablish when it would, validated on a synthetic positive control containing a genuine cross-packet dependency.

arXiv AI Papersel mes pasado

DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs

Speech-LLMs often exhibit prompt overfitting, where models solely trained on automatic speech recognition (ASR) instruction fail to generalize to new instructions such as speech translation and continue to behave primarily as ASR system. We propose DirectSpeech2LLM, a simple end-to-end framework that preserves the instruction-following ability of the LLM on unseen tasks when conditioned on speech. It computes distance-based CTC loss over the frozen LLM embedding matrix and uses greedy CTC labels to derive geometrically and temporally aligned speech embeddings respectively as an input to the LLM. Trained solely on 960 hours of LibriSpeech ASR data, DirectSpeech2LLM outperforms the cascaded system on ASR (seen task) and generalizes zero-shot to speech translation and emotion recognition (two unseen tasks), closely matching the cascaded system upper bound on these two new instructions despite seeing neither during training. We also find that geometric alignment strength plays a smaller role than previously assumed, as our modified CTC loss is shown to provide sufficient implicit geometric grounding without requiring an explicit regression loss. Results are consistent across two LLM families and scale with both more training data and model capacity.

arXiv AI Papersel mes pasado

POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents

LLM tool-use agents operate in dynamic environments where many actions carry operational risk. However, most safety mechanisms react only after errors manifest. Existing pre-emptive approaches either fine-tune the agent on chain-of-thought deliberation or compile natural-language guardrails into runtime checks, but they do so without exposing a structural, auditable verdict. We propose POLAR, a guardrail framework for small tool-calling agents that assesses reversibility through a structured two-layer ontology. POLAR assigns each action a graded reversibility score by deriving a candidate inverse sequence; calls failing a threshold are pruned before execution. Evaluated on τ^2-bench across six agent models, POLAR improves mean task reward by 0.11 to 0.18 points on airline for four of six agents, but only eight of eighteen model--domain cells improve overall; retail and stronger agents often regress. POLAR provides an auditable structural check and characterizes its task-utility trade-offs. Reward is not a direct measure of prevented harm.

arXiv AI Papersel mes pasado

SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning

Frontier LLM agents have been shown to be capable of solving increasingly complex tasks for which humans have measurable solutions. This begs the pertinent question of whether LLM agents can go beyond what humans have already solved. The ability to develop sophisticated strategies to tackle consequential problems becomes paramount as well-trodden, human-developed solutions become insufficient for problems for which we lack context or enough training data. We study agents' capability of such strategy formation through the communal practice of video game speedrunning. In speedrunning, practitioners compete to find the fastest way to complete a video game under certain conditions, and in so doing uncovering interesting unorthodox play styles that require a thorough understanding and mastery of the underlying game mechanics. We introduce SPEEDRUNBENCH, a benchmark that evaluates frontier LLM agents across 9 different games. To perform well in this benchmark, agents must repeatedly improve their strategy, reflect on their performance, exploit their gained knowledge, and reason across a long-horizon of actions to improve on an increasingly difficult problem: being faster than themselves and everyone else. Our experiments show that while frontier agents approach human world records in simple platformer games, they remain behind human performance on longer, more complex games under practical budgets. These results suggest that SPEEDRUNBENCH is a useful testbed for studying agents' strategy formation capabilities as well as being a saturation-resistant evaluation measure, as there is almost always a faster completion time waiting to be discovered.

arXiv AI Papersel mes pasado

HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR

This paper presents the HINTT system submitted to the 2nd Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM). We address multilingual speaker-attributed ASR, where systems must determine who spoke when and what was spoken. We investigate two modeling strategies for this problem: a cascaded pipeline that combines speaker diarization with speech-LLM-based ASR, and a unified speech LLM that directly generates speaker labels, timestamps, and transcriptions. Our final submission is based on the cascaded pipeline, consisting of a fine-tuned DiariZen diarization model, a fine-tuned Qwen3-ASR model, and LLM-based generative error correction. For comparison, we also fine-tune VibeVoice-ASR as a unified model using the same official training data. All task-specific fine-tuning and model selection are performed using only the official MLC-SLM data, without external data or pseudo-labels. Experimental results demonstrate that the cascaded system remains more reliable under the MLC-SLM Task 1 conditions, while unified speech LLMs offer a promising direction for future speaker-attributed ASR.

arXiv AI Papersel mes pasado

Language Carries the Expert's Impression: Instrument-Anchored LLM Judges Transfer Counseling-Quality Assessment and Beat In-Domain Training

Automatic assessment of communication quality in dyadic counseling conversations is bottlenecked by data: expert-rated corpora are small and expensive to grow. We study cross-domain transfer of expert overall-impression prediction across three German corpora of simulated counseling (two general-practice medical, one school-related parent-teacher; n=195 expert-rated sessions, one corpus after scale equating). Training on the other domains beats training in-domain: leave-one-domain-out transfer reaches nested Spearman ρ= 0.54 against 0.48 within the target domain, a paired session-level gap of +0.15 that holds at +0.12 when the training-set sizes are matched, so it is not simply data volume. The decisive features are session-level construct scores from small open-weight LLMs reading the two-speaker transcript, with the constructs largely derived from the experts' rating instruments: the instrument-derived battery lifts a single judge from 0.32 to 0.41 over generic dialogue qualities, judges from three model families ensemble to 0.51 language-only, and a nonverbal-dyadic block adds +0.03 more, not separable from noise at this sample size. We also price the recording setup: one corpus lost its per-speaker audio, 16% of its diarised segments carry the wrong speaker, and repair is worth +0.07 there. At practically attainable corpus sizes, the expert's overall impression is carried by what is said, and by other communication programs' data more than by one's own.

arXiv AI Papersel mes pasado

DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks

LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conventions on their own. Without memory of past attempts, they repeat the same mistakes across tasks, leading to more task failures and longer trajectories. To address this, agentic systems typically rely on human-written guidelines or on procedural memory built from training tasks and an oracle verifier, both of which require prior knowledge of the environment. We present DAEDALUS, a method for bootstrapping reusable agent memory from self-generated practice without existing tasks or oracle verifiers. DAEDALUS pairs two agents: an explorer that interacts with the environment to generate challenging yet solvable tasks, and a solver that attempts them. A heuristic is derived from each solver failure and accepted only after the solver repeatedly succeeds with that heuristic in context. These outcomes also provide feedback for the explorer to refine the difficulty of future tasks. Accepted heuristics are then consolidated into a memory bank for test-time use. Across AppWorld, τ^2-bench, and AutomationBench, DAEDALUS improves mean success rates by up to 15.9 points and pass^5 by up to 2.2x over a no-memory baseline, and is competitive with methods using training tasks, at a lower inference cost than most. We show that performance gains already emerge with a small exploration budget, and that its heuristics also benefit agents from other model families. Our ablations further reveal that solver traces provide the key information needed to derive effective heuristics, while factorizing early discoveries makes exploration more cost-efficient. Beyond memory construction, we find that the tasks generated by DAEDALUS can serve as a proxy for benchmark tasks when ranking models by performance. Code and artifacts: www.github.com/illuin-tech/daedalus.

arXiv AI Papersel mes pasado

Are Language Models Script-Aware?

Language models frequently generate outputs in unintended languages or scripts, a phenomenon known as off-target generation. While existing research has focused on language selection, the dimension of script knowledge remains understudied: before any linguistic understanding can occur, users must recognize the graphic symbols in a model's response. We investigate whether Small and Large Language Models (SLMs and LLMs) possess script knowledge by testing them on multi-scriptic languages. Through two complementary experiments, we evaluate whether models (1) adapt their output script to match the input, and (2) follow explicit instructions to generate text in a specified script. The models we tested demonstrate substantial script knowledge: they all achieve a near-perfect Latin script fidelity (more than 98%) and follow script instructions with high frequency. Nevertheless, we notice differences between LLMs and SLMs, with higher scores for LLMs including for non-standard script combinations.

arXiv AI Papersel mes pasado

The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation

In recent years, several methods for detecting when large language models (LLMs) hallucinate have been developed. These methods are often benchmarked with open-domain question answering (QA) datasets containing questions and corresponding short reference answers. First, an LLM is used to generate answers to questions within the QA dataset. Then, some automated labeling strategy is used to label these answers as hallucinated or not by comparing them with the reference answers in the dataset. This evaluation setting creates a methodological ambiguity between two criteria: reference faithfulness (whether the answer is fully supported by the reference) and factual correctness (whether the answer is free from contradictions and factually false specific claims). In practice, automated labelers may apply the former criterion even when the intended target is the latter. We study this potential criterion mismatch using 900 human-labeled question-answer pairs spanning three commonly used QA datasets and three generator models, with labels targeting answer-level factual correctness. We evaluate lexical similarity metrics, a reference-entailment NLI baseline, and seven LLM judges under controlled prompt variants as automated labelers. Our experiments reveal substantial disagreement both among automated labeling strategies and between these labels and human annotations. Many strategies also exhibit strong directional error biases, and for most judge-generator pairs, replacing a faithfulness-oriented prompt with a factual-correctness prompt improves agreement with human annotations and reduces false-positive dominance, indicating that automated hallucination labels depend strongly on how the target criterion is specified. Label-source choice should therefore be considered a fundamental part of benchmark design and made explicit, validated, and matched with the benchmark goal.

arXiv AI Papersel mes pasado

Structured but Silent: Probing Capability Requirements in LLM Hidden States

Reliable tool use requires more than triggering a mechanism or matching a query to an API description. Before selecting a specific tool, an agent must first infer the capability requirements implied by the user query. In this paper, we investigate whether these query-side capability requirements are linearly decodable from LLM hidden representations prior to generation, and how this hidden-state accessibility compares with explicit verbal classification. We introduce TACIT, a framework that decomposes external requirements along three fundamental axes: Source, Transformation, and World Effect, defining eight structurally distinct capability classes. Using 1,600 balanced training queries from benchmarks, synthetic examples, and new domain scenarios, we train linear probes on pre-generation hidden states from four open-weight LLM families. Our empirical results demonstrate that fine-grained capability structures are linearly decodable with high accuracy across all models. Crucially, however, we expose a representation-to-verbalization gap: these same models are significantly less reliable when asked to explicitly classify the same queries in natural language. This disconnect indicates that information about required external capabilities is linearly accessible in LLM hidden representations but not reliably expressed, a phenomenon we define as "structured but silent."

arXiv AI Papersel mes pasado

VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs

Multimodal large language models have become the dominant paradigm for visual understanding, but incur substantial costs by encoding inputs into dense, fixed-size patch tokens. However, visual information is unevenly distributed: some regions require fine-grained detail, while others admit compact representations. Downsampling sacrifices this detail, while existing token pruning and adaptive approaches remain limited in content-adaptive granularity, task generalization, and integration with modern MLLMs and serving infrastructure. Overcoming these limitations calls for foundation models that learn, end to end, where-and at what granularity-to allocate visual representations, a native capability we term elastic visual representation weaving. We introduce VisionWeave, establishing this capability in frontier-level MLLMs through large-scale training. It combines two components: a gated spatial pooler constructs coarse-grained representations alongside native fine-grained representations within a shared MRoPE coordinate, while a granularity router learns their content-adaptive allocation. Through self-distillation alone, we validate this capability on Qwen3.5-4B and scale to Qwen3.8-27B with over 30K A100 GPU-hours. Based on Qwen3.8-27B, VisionWeave adaptively adjusts token savings to visual content, saving 43.0% tokens on average while retaining 98.9% native performance across eight benchmarks, versus only 88% performance preserved for token pruning baselines with a fixed 50% savings target. Extensive evaluations confirm robust efficiency-quality trade-offs across diverse tasks, resolutions and video frames. When deployed on SGLang serving engine, our method achieves a 2.3x throughput gain while reducing mean TTFT by 54.4% and mean TPOT by 60.6%. Together, we believe these results position elastic visual weaving as a promising capability for next-generation multimodal models.

Hugging Face Blogel mes pasado

Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance

AWS Machine Learning Blogel mes pasado

Introducing GLM 5.3 on Amazon Bedrock

GLM 5.3 from Z.ai is now available on Amazon Bedrock: a 753B-parameter mixture-of-experts model built for coding and long-horizon agentic tasks. Learn how to invoke it with the OpenAI-compatible APIs, cut cost and latency with prompt caching, and run an authorized security test with the open-source Strix agent.