Tema

LLMs

3009documentos

250últimos 7 días

Omni-Modal LLMs Know More Than They Say

Omni-modal large language models (Omni-LLMs) extend LLMs to process heterogeneous modalities (e.g., vision, audio, and IMU signals) alongside language, enabling a broader range of multimodal tasks. Yet we find that these models often fail to express information from non-textual modalities even when they perceive it correctly. We term this disconnect knows-but-cannot-say. To investigate this phenomenon, we introduce Token-level Modality Alignment (TMA), which measures the alignment between individual modality representations and response representations. Our analysis shows that non-textual representations are less aligned with response tokens and receive less attention than textual representations, suggesting a potential explanation for uneven modality preferences. Motivated by these findings, we propose OmniCatalyst, a simple perceive infer strategy that complements the original modality inputs with self-generated text, making non-textual knowledge more accessible. Across seven Omni-LLMs, OmniCatalyst consistently improves performance (+7.29%) and yields more balanced modality preferences, with further gains from diverse training strategies. Further analysis demonstrates that the knowledge extraction phases increase TMA, suggesting that improved alignment makes non-textual information more accessible during response generation. In summary, our findings uncover how Omni-LLMs can better express modality knowledge through language. Our code is available at https://github.com/naver-ai/OmniLLM.

arXiv AI Papersel mes pasado

Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving

Puzzles offer a natural testbed for Large Language Models (LLMs) reasoning because they pose verifiable goals under partial information and require multi-step decisions to reach a solution. However, existing puzzle benchmarks typically focus on narrow environments with rigid mechanics and tightly constrained solution targets. To bridge this gap, we introduce the Active Probing Benchmark (APB), which generalizes puzzle-solving by casting concept identification as an interactive reasoning task that integrates specialized knowledge assessment into the puzzle setting. Specifically, APB evaluates whether models can acquire information via multi-turn active probing and inference to pinpoint 960 target concepts of specialized difficulty across eight diverse academic domains. Our evaluation reveals a counter-intuitive phenomenon: most open-source reasoning models significantly underperform their standard instruction counterparts. This finding suggests that in interactive settings, these models struggle to leverage procedural reasoning to reliably access and apply specialized domain knowledge. Beyond these empirical insights, APB provides a scalable pipeline for generating benchmarks that probe knowledge reasoning under interaction across diverse settings.

arXiv AI Papersel mes pasado

PID-Gated Continual Prompt Adaptation Under Noisy Feedback

Deploying LLM agents in non-stationary environments requires continually revising their instructions as the task drifts, yet rewriting after every reported mistake can turn noisy feedback into persistent errors. This raises an often-overlooked scheduling question in prompt adaptation: when should feedback trigger a lasting instruction update, and at what editor-call cost? Taking inspiration from proportional-integral-derivative (PID) control, we introduce a family of lightweight gates that react to the current error, accumulate evidence over time, and roll back deterioration after an edit. We benchmark these gates against both simple baselines and advanced prompt optimizers (TextGrad and GEPA), over a diverse suite of drifting tasks, LLM parameter sizes, feedback-noise levels, and random seeds. PID-gated continual prompt adaptation yields a more favorable Pareto trade-off between task performance (high accuracy, low error) and editor-call budget than the baselines considered, pointing to control-theoretic scheduling as a simple, general tool for robust prompt adaptation under unreliable feedback.

arXiv AI Papersel mes pasado

Towards a Benchmark for Fire Safety Code Interpretation in the Hong Kong AEC Industry

Large Language Models (LLMs) are increasingly explored in the Architecture, Engineering, and Construction (AEC) domain, yet their reliability in regulatory compliance remains uncertain. In this study, we evaluate the performance of LLMs on Hong Kong fire safety codes. In collaboration with domain experts, we create a localized benchmark dataset comprising both multiple-choice questions (MCQs) and open-ended questions (OEQs) to evaluate 12 widely used proprietary and open-source models. Our findings show that top-performing proprietary models achieve 80-90% accuracy on MCQs, whereas open-source models generally lag behind. However, on open-ended evaluation, expert human assessments reveal an accuracy range of only 50-70%, demonstrating that LLMs still have substantial room for improvement in specialized compliance tasks.

arXiv AI Papersel mes pasado

Scaling Multi-Agent Intelligence with Substrate-Centric Coordination

Existing large language model (LLM) based multi-agent systems have been shown to scale poorly, and we identify three problems: reading burden that grows with the group, useful information diluted by shared work of unknown quality, and fragility to failed agents. We argue that the problems are largely due to agent-centric designs: the coordination structure is wired into fixed workflows, central coordinators, or peer-to-peer messaging, and recent blackboard-style methods that move the coordination into a shared medium relieve only the last problem. To close the gaps, we build ScaleMAS, where asynchronous agents interact with a shared datastore of linked messages via three operations: publishing messages with optional references to earlier ones that they build on, searching for messages by content, and visiting messages by address. Search returns at most k messages, so an agent's read stays bounded at any group size; results are ranked by relevance and by how often they are cited, which we find to be an effective proxy for quality; and messages persist after their producers leave, so the group carries on when individual agents fail. Across four agentic tasks, ScaleMAS outperforms agent-centric and blackboard-style baselines at lower inference compute, continues to scale up to 128 agents, and tolerates losing agents midway.

arXiv AI Papersel mes pasado

Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding

Hour-long videos, streaming feeds, and movie-length content are pushing vision-language models (VLMs) past their breaking point -- the standard recipe of encoding each frame into visual tokens yields sequences that grow linearly with video length, causing prohibitive memory consumption and inference latency. Existing approaches, such as token reduction and keyframe selection, shorten the token sequence but leave the O(n) scaling intact, failing to resolve the fundamental bottleneck. We propose FramePack-U, a strikingly simple, training-free frame packing framework that compresses arbitrarily long videos into a fixed size visual representation at constant memory cost. FramePack-U requires no fine-tuning or architectural modification -- it plugs directly into off-the-shelf VLMs at inference time. Inspired by FramePack from the generation literature, we propose a content-aware compression strategy for visual understanding under a fixed token budget. Specifically, FramePack-U (1) scores each frame by its semantic similarity to the text prompt and ranks frames in a diversity-driven manner, and (2) packs the selected frames at varying resolutions into a fixed-length context window. This concentrates the memory budget on frames that are both instruction-relevant and visually diverse. While FramePack-U can in theory pack arbitrarily many frames into the fixed budget, we identify an empirical instantiation that generalizes robustly across settings. Extensive experiments on LongVideoBench, MLVU, and Video-MME show that FramePack-U consistently outperforms full-resolution baselines and prior token reduction and keyframe selection methods across diverse model families, parameter scales, and frame budgets. Notably, on Qwen3.5-35B-A3B with a 128-frame budget, FramePack-U yields gains of +12.9\%, +10.6\%, and +9.7\% over the official model on the three benchmarks, respectively.

arXiv AI Papersel mes pasado

Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues

LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary expertise. Yet existing systems and evaluations largely rest on an implicit perfect-colleague assumption: collaborators provide correct and complete information and respond promptly to requests. In realistic teamwork, however, collaborators may return information that does not answer the intended question, provide insufficient detail to support a decision, or fail to respond to a request. To separate task-solving competence from the ability to recover an unreliable evidence-gathering process, we introduce the Unreliable Colleagues Benchmark (UnCoBench), which organizes behavioral failures through Misaligned, Incomplete, and Missed settings. The main agent need to verify contextual correctness, diagnose information gap and track unresolved dependencies in order to obtain the correct evidence for solving the task. We also introduce a verifiable and scalable automated generation pipeline that pairs LLM-based scenario generation with executable checks of answer uniqueness and role necessity. Results across ten models show that similar reliable-setting performance can result in different robustness to unreliable evidence. Trace analysis reveals frequent omissions of corrective follow-up, and the recovery behavior involves inefficient waiting and redundant queries. These findings show that robust collaboration requires not only sound reasoning, but also targeted action to diagnose evidence failures, recover relevant information, and integrate it into decisions. Our data and source code are available at https://github.com/iNLP-Lab/UnCoBench.

arXiv AI Papersel mes pasado

Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR

Reinforcement learning with verifiable rewards (RLVR) typically uses small rollout groups per prompt, where repeated sampling from the same policy can yield highly similar trajectories, reducing within-group reward variation and weakening group-relative advantage signals. Existing remedies such as higher sampling temperature, entropy bonuses, asymmetric clipping, and larger rollout budgets broaden sampling or modify policy updates but leave rollout conditioning unchanged. In this paper, we propose EDEN (Embedding-space Directional Exploration via anchored Noise), which intervenes at the rollout source through anchored input perturbations. EDEN explores beyond the policy's own rollouts. Within the same rollout budget, it replaces a small fraction of standard rollouts in each group with rollouts that the same policy generates from the prompt plus a single appended, perturbed embedding position, rather than from the prompt alone. Gaussian noise drives variation, while a shared anchor provides a common conditioning direction within each prompt group. Selected perturbed rollouts contribute to GRPO updates with downweighted advantages, and the model architecture, discrete decoding, and test-time inference remain unchanged. Across model scales and mathematical reasoning benchmarks, EDEN outperforms GRPO and the exploration controls evaluated in the same pipeline, with the largest gains in sampled solution coverage. Analyses show that more prompt groups provide non-zero group-relative learning signals and that noise and anchoring play complementary roles. Intervening at the rollout source is thus an effective lever for exploration in RLVR.

arXiv AI Papersel mes pasado

SelectTTRL: Representation-Guided Data Selection for Efficient Test-Time Reinforcement Learning

Test-Time Reinforcement Learning (TTRL) enables large language models to adapt directly on unlabeled test problems by constructing pseudo-labels from multiple sampled responses. However, existing TTRL methods typically apply the same expensive sampling and optimization procedure to all test problems, despite substantial differences in their training utility. In this paper, we study whether such problems can be identified before costly test-time training, without access to ground-truth answers. We uncover a stable relationship between internal response representations and problem-level empirical accuracy. Specifically, we define COS as the cosine similarity between a model's response representation and a correctness-related direction constructed from an independent question-answering dataset. COS consistently correlates with problem solvability across different models, datasets, and experimental settings, and we further provide a theoretical analysis explaining this relationship. Building on this finding, we propose SelectTTRL, a representation-guided data selection method that ranks test problems using COS and applies TTRL only to a selected percentile interval. SelectTTRL leaves the standard TTRL pipeline unchanged for the selected problems, while avoiding unnecessary multi-response sampling and reinforcement learning updates on the remaining ones. Experiments across multiple reasoning benchmarks demonstrate that SelectTTRL substantially reduces test-time computation while maintaining or improving the performance of standard TTRL. Code is available at https://github.com/heyiliyi/SelectTTRL-public.

arXiv AI Papersel mes pasado

The Sharp Directions Are Against You: Curvature Analysis of Activation Steering

Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for behavioral control. The standard construction, contrastive activation addition (CAA), is fragile, as on many inputs it shifts behavior in the wrong direction. To explain this fragility, we first study the geometry of the steering vector. We introduce steering Hessian, the matrix of second order derivative of the model's behavioral loss with respect to the steering vector. It captures the output behavior response sensitivity of the model under small perturbations of the steering vector along each direction. Its top eigenvectors are sharp directions: tiny perturbations along them can cause large, erratic, input-dependent behavioral swings. Bottom eigenvectors are flat directions: behavior is robust along them. Removing the sharp component of a steering vector approximately preserves its direction and magnitude (cosine > 0.974, norm reduction < 3% for typical settings) while reducing the vector's directional curvature by up to 12x (median 4x across 36 conditions). We evaluate on three model families (Qwen2.5-7B, Llama-3.1-8B, Mistral-7B), with four behavioral tasks, and 36 token-level conditions. Steering along sharp directions reverses the intended behavior in every condition tested, with anti-steer rates of 53-100%. Sharp directions account for only 1-5% of the CAA vector's squared norm. However, they drive a disproportionate share of the gap between the steered and unsteered next-token distributions during autoregressive generation. We term this one-line correction as sharp removal; it outperforms standard CAA in open-ended generation across all 25 conditions tested. A jailbreaking experiment further shows that sharp directions act as noise rather than signal: they disrupt coherent behavioral control regardless of steering polarity.

arXiv AI Papersel mes pasado

Heterogeneous Agentic Coevolution

Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence. However, many domain-specific applications rely on specialized foundation models that possess strong domain expertise but remain dependent on human-designed improvements. Extending recursive self-improvement to these models presents a key challenge: as a specialist improves, the strategies used to advance it must also adapt. To address this challenge, we propose Heterogeneous Agentic CoEvolution (HACE), a framework that jointly evolves specialized foundation models and LLM agents through reciprocal learning. HACE improves the specialist through supervised learning while training the agent with on-policy reinforced self-training, guided by verified performance gains on the current specialist. The agent's exploration, in turn, informs subsequent specialist training, enabling both models to adapt to each other's progress. To sustain this reciprocal learning, HACE further employs evolutionary search to optimize their interaction harness, adapting how the models exchange information and select training experiences as their capabilities evolve. We evaluate HACE across three challenging domains: recommendation systems, protein function prediction in biology, and crystal stability prediction in material discovery. We show that HACE outperforms the evaluated self-improving methods on the primary task metrics across all three domains. These results shed light on heterogeneous coevolution as a universal approach to improving specialized foundation models through reciprocal interaction with a learning agent.

Apple Machine Learning Researchel mes pasado

Self-Compacting Language Model Agents

Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaffolds mitigate it with fixed-interval compaction triggered at a token threshold. Such triggers pay no heed to trajectory structure, risking discard of partial results mid-derivation or mid-search. We propose SELFCOMPACT, a scaffold that allows the…

Apple Machine Learning Researchel mes pasado

Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged

Large Language Models (LLMs) are considered to be a more efficient and cost-effective alternative to human judgment for Machine Translation (MT) evaluation. With MT evaluation spanning a large number of language pairs, domains and levels of annotation granularity, LLMs must be thoroughly evaluated across these dimensions before being reliably used as alternatives to human evaluation. In this paper, we evaluate…

Hacker News (AI)el mes pasado

The gap in shared understanding of LLM capability is widening

en▲ 28

Hacker News (AI)el mes pasado

LLM Pareto Frontier over time [video]

it▲ 5

arXiv AI Papersel mes pasado

Structural Chain-of-Thought: Reasoning with Executable Computational Graphs

Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, and not always faithful. We introduce a Structural Chain-of-Thought framework where models generate executable computational graphs instead of free-form reasoning. The final answer is obtained by deterministically executing the graph. The model is trained using graph-based reinforcement learning that rewards structural validity, answer correctness, and node overlap with reference graphs. Experiments across five benchmarks and four model families show that our method consistently improves accuracy over supervised graph training and can reduce generation length by up to 5-6x compared with standard GRPO and chain-of-thought supervised training. Our faithfulness experiments reveal that models trained with our approach tend to rely on deriving their answers from the generated graphs rather than producing post-hoc rationalizations as usually in chain-of-thought reasoning.

arXiv AI Papersel mes pasado

Anchors Enhance Controllability and Reasoning of Diffusion Language Models

Diffusion language models (DLMs) offer new opportunities for controllable text generation. However, their controllability, defined as the ability to satisfy task constraints while preserving their original capabilities, remains underexplored. DLMs' bidirectional attention allows control tokens to guide generation from arbitrary positions in the output sequence, but effective guidance depends on the compatibility between their content and placement. To this end, we propose AnchorDLM, a framework in which an anchor generator produces an anchor consisting of a short output fragment and its position for each query. The anchor is placed as control tokens at the specified position to initialize the output sequence of a frozen DLM and guide subsequent denoising. We train the anchor generator with reinforcement learning (RL) to jointly optimize anchor content and placement, using rewards computed from the DLM's generated outputs based on answer correctness and constraint satisfaction. Moreover, through the lens of discrete flow matching (DFM), we interpret anchor placement as helping to reshape the initial velocity field that guides generation. Experiments on code generation and mathematical reasoning across five DLM backbones show that AnchorDLM improves controllability and further yields gains in reasoning performance across diverse benchmarks.

arXiv AI Papersel mes pasado

Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families

LLM multi-agent systems split work across agents that communicate through text. An agent summarizes its findings, another agent receives the text. This constrains communication to discrete tokens and costs redundant compute, limiting bandwidth and capabilities of multi-agent systems. Recent works demonstrate KV-cache transfer between LLMs but they either require the LLMs to be within the same family or cannot function across context, thus requiring the receiver to prefill text. We present SwaT (Swarm Telepathy), the first cross-family KV-cache transfer method that allows prefill-free communication in multi-family multi-agent systems. In an agent-to-agent communication setting, combining SwaT with recent advances in KV-cache compaction beats text-to-text communication in both accuracy and speed, with a mean of 40\% higher accuracy and a mean of 4faster wall-clock time. Experiments show SwaT achieves high performance on 17 benchmarks across 12 LLMs and 6 families. Additionally, given a sender Vision-Language Model (VLM), SwaT is able to transfer the vision capabilities to a text-only receiver LLM exceeding text-to-text communication despite SwaT being trained on text-only data. SwaT keeps both sender and receiver models frozen without fine-tuning and only requires <50M tokens and <1 GPU-day to train.

arXiv AI Papersel mes pasado

TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents

AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next. We call the design of this process loop engineering, which includes context management, model selection, compaction, and termination. Existing efficiency work mainly compresses tool observations or routes selected turns to cheaper models, but the practical opportunity for these optimizations remains unclear. We analyze 600 publicly released coding-agent trajectories spanning two agent scaffolds and two language models. Median observations contain only 118-286 tokens, while the large build logs commonly used to motivate compression occur near the ninety-ninth percentile. Moreover, 98.6% of input tokens are served from a prefix cache, so flat input pricing overestimates loop cost by roughly 7x on average under near-ideal caching. We derive and empirically validate a closed-form break-even condition for model delegation. Delegation increases cost in half of the evaluated settings, near the predicted boundary. More broadly, turn count explains 84% of the variance in log trajectory cost, compared with 4% for mean observation size; the most expensive trajectories have the most turns despite having the smallest observations. These associations suggest that observation-focused methods target a secondary cost factor, and identify unnecessary turns as the larger and largely unexamined opportunity, though we do not establish that turns can be removed while holding task success fixed. We release TurnCost, a tool for re-scoring trajectory corpora under alternative caching, pricing, compression, and routing policies.

arXiv AI Papersel mes pasado

Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions

Argument structures represent how individual arguments interact within a discourse. However, leveraging these structures to infer meaningful knowledge remains challenging, as it requires a formal representation of how argumentative influence propagates across the structure. We propose Neuro-symbolic Argumentation Reasoning System (NARS) for performing persuasiveness detection directly from online discussions. The neural component employs retrieval-augmented iterative LLM reasoning to extract bipolar argument structures, while the symbolic component applies gradual argumentation semantics to propagate argumentative influence over the structure. Using the Webis-CMV-20 corpus, we construct CMV2BAS, a dataset of long, multi-threaded ChangeMyView discussions annotated with LLM-derived bipolar argument structures and labeled with delta events (view change vs.\ no change). We investigate whether gradual argumentation semantics can effectively detect persuasiveness, whether augmenting them with argument quality and graph-based centrality improves performance, and whether symbolic reasoning remains necessary in the presence of modern LLMs. NARS achieves F1=0.57 and AUC=0.56 under its best configuration, outperforming zero-shot Qwen3.6:27B and GPT-oss:20B. We identify support-dominant discussions and long argumentative chains as key failure modes limiting attack influence propagation. Our work demonstrates the feasibility of operationalizing formal gradual argumentation semantics over noisy real-world discourse for scalable macro-level persuasion analysis, while highlighting key challenges and directions for future research in neuro-symbolic argumentation reasoning. We release both CMV2BAS dataset and the NARS framework for public use.