Multimodal Large Language Models (MLLMs) excel at recognizing individual visual elements and reasoning over simple linear diagrams. However, when faced with complex topological structures involving branching paths, converging flows, and cyclic dependencies, their reasoning capabilities degrade sharply, even on tasks as basic as counting endpoints. Existing benchmarks fail to probe this gap, focusing on semantic comprehension rather than structural reasoning. We introduce ReactBench, a benchmark that reveals fundamental limitations in structural reasoning through chemical reaction diagrams. These real-world scientific diagrams offer an ideal testbed because they naturally span diverse structures from linear chains to cyclic graphs, while requiring both precise local recognition and coherent global reasoning. Our benchmark comprises 1,618 expert-annotated QA pairs across four hierarchical task dimensions. Extensive evaluation across 24 MLLMs reveals a significant performance gap exceeding 30% between anchor-based tasks and holistic structural reasoning tasks. Controlled ablations confirm this bottleneck lies in reasoning, not perception. These findings expose a fundamental deficit in structural understanding and establish directions for advancing visual reasoning.
Qiang Xu, Shengyuan Bai, Yu Wang et al.· 0 citations
Designing effective heuristics for NP-hard combinatorial optimization problems remains challenging and often requires substantial domain expertise. Recent LLM-guided evolutionary methods have shown promise for automated heuristic generation, but most existing approaches refine heuristics independently or through limited pairwise feedback. We propose ReVEL: Multi-Turn Reflective LLM-Guided Heuristic Evolution via Structured Performance Feedback, a framework for group-wise multi-turn heuristic refinement. ReVEL organizes heuristics into behavior-aware reflective groups, including similarity-driven groups for localized refinement and diversity-driven groups for exploratory search. Within each group, the LLM performs iterative multi-turn refinement using accumulated performance feedback, enabling related heuristics to be jointly analyzed and progressively improved across evolutionary iterations. Experiments on standard combinatorial optimization benchmarks show that ReVEL generally improves optimization performance over existing LLM-guided evolutionary baselines across multiple settings and LLM backbones. Additional analyses suggest that behavior-aware grouping contributes to more consistent refinement trajectories during iterative heuristic evolution.
Cuong Van Duc, Minh Nguyen Dinh Tuan, Tam Vu Duc et al.· 0 citations
Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and question answering, have been developed to aid in understanding scientific literature. However, these tools lack the structured, multi-step approach necessary for extracting deep insights from scientific literature. Large Language Models (LLMs) offer new possibilities for literature analysis, but remain unreliable due to hallucinations and incomplete extraction. We introduce Elhuyar, a multi-agent, human-in-the-loop system that integrates LLMs, structured AI, and human scientists to extract, analyze, and iteratively refine insights from scientific literature. The framework distributes tasks among specialized agents for filtering papers, extracting data, fitting models, and summarizing findings, with human oversight ensuring reliability. The system generates structured reports with extracted data, visualizations, model equations, and text summaries, enabling deeper inquiry through iterative refinement. Deployed in materials science, it analyzed literature on tungsten under helium-ion irradiation, showing experimentally correlated exponential helium bubble growth with irradiation dose and temperature, offering insight for plasma-facing materials (PFMs) in fusion reactors. This demonstrates how AI-assisted literature review can uncover scientific patterns and accelerate discovery.
Maxwell J. Jacobson, Daniel Xie, Jackson Shen et al.· 0 citations
We observe that an agent trace is a structured document. A coding agent session contains user turns, assistant text, chain of thought blocks, tool calls, tool results, subagent invocations, compaction boundaries, and harness injected directives, and may exceed ten thousand JSONL lines. Effective trace analysis requires a lossless record, a session level overview, and content retrieval with conversational roles. To this end, we propose VCC, namely View oriented Conversation Compiler, which lexes, parses, and lowers a raw JSONL log into three views based on one intermediate representation. The full view provides the lossless transcript and defines the line number coordinate system. The UI view reconstructs the interaction perceived by the user. The adaptive view selects relevant trace content and preserves role annotations and line range pointers. Line numbers are assigned before view lowering, ensuring that all pointers can be resolved to the full view. We evaluate VCC in a context engineering experiment on AppWorld by varying the input format of the reflector. Experiments with three model configurations and two test splits show that VCC improves aggregate task goal pass rates by 1.1 to 4.2 points, reduces reflector token consumption by one half to two thirds, and generates smaller memory files. These results demonstrate the effectiveness of trace format as an important component of context engineering infrastructure.
Lvmin Zhang, Maneesh Agrawala· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault trees stored as images to be directly processed by large language models, which can assist in tracking and analyzing malfunctions, we propose a novel textual representation of fault trees. Building on it, we construct a benchmark for multi-turn dialogue systems that emphasizes robust interaction in complex environments, evaluating a model's ability to assist in malfunction localization, which contains $3130$ entries and $40.75$ turns per entry on average. We train an end-to-end model to generate vague information to reflect user behavior and introduce long-range rollback and recovery procedures to simulate user error scenarios, enabling assessment of a model's integrated capabilities in task tracking and error recovery, and Gemini 2.5 pro archives the best performance.
Yuhui Wang, Zhixiong Yang, Ming Zhang et al.· 0 citations
While retrieval-augmented generation (RAG) enhances LLM performance, it does not eliminate hallucinations, making accurate detection essential. Uncertainty-based methods are attractive for this purpose because they can be integrated into real-world pipelines with little overhead. One of the most widely used uncertainty signals is predictive entropy. We show, however, that entropy can be unreliable in RAG settings and trace this limitation to two opposing internal effects. Induction heads, which copy patterns from earlier context, causally support correct responses and lower predictive entropy, but they also appear to co-activate entropy neurons that push it back up. As a result, correct, context-grounded responses can still receive high uncertainty scores. To address this, we propose INTRYGUE (Induction-Aware Entropy Gating for Uncertainty Estimation), a training-free, mechanistically grounded method that gates predictive entropy by an attention-based estimate of induction-head activity. Evaluated across four RAG-style benchmarks and six open-source LLMs (4B to 13B parameters), INTRYGUE performs competitively against a wide range of baselines, matching or exceeding the strongest of them in most settings. Our findings suggest that hallucination detection in RAG benefits from combining predictive uncertainty with interpretable internal signals of context utilization.
Alexandra Kuleshova, Andrei Volodichev, Daria Kotova et al.· 0 citations
Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked when applied to knowledge-intensive domains (e.g., healthcare and law). They either rely on a static library of general nodes like Chain-of-Thought, which lack specialized expertise, or attempt to generate nodes on the fly. In the latter case, the orchestrator is not only bound by its internal knowledge limits but must also simultaneously generate domain-specific logic and optimize high-level topology, leading to a severe architectural coupling that degrades overall system efficacy. To bridge this gap, we propose Unified-MAS that decouples granular node implementation from topological orchestration via offline node synthesis. Unified-MAS operates in two stages: (1) Search-Based Node Generation retrieves external open-world knowledge to synthesize specialized node blueprints, overcoming the internal knowledge limits of LLMs; and (2) Reward-Based Node Optimization utilizes a perplexity-guided reward to iteratively enhance the internal logic of bottleneck nodes. Extensive experiments across four specialized domains demonstrate that integrating Unified-MAS into four Automatic-MAS baselines yields a better performance-cost trade-off, achieving up to a 14.2% gain while significantly reducing costs. Further analysis reveals its robustness across different designer LLMs and its effectiveness on conventional tasks such as mathematical reasoning.
Hehai Lin, Yu Yan, Zixuan Wang et al.· 0 citations
Large Language Models (LLMs) are increasingly serving as personal assistants, where users may share individual preferences over extended interactions. However, assessing how well LLMs can follow these preferences in natural, long-term situations remains underexplored. This work proposes RealPref, a benchmark for evaluating natural preference-following in personalized user-LLM interactions. RealPref features 100 synthetic user profiles, 1300 personalized preferences, 4 types of preference expression (from explicit to implicit), and long-horizon interaction histories. It explored three types of test tasks (multiple-choice, true-or-false, and open-ended), with granular rubrics for LLM-as-a-judge evaluation. Results indicate that LLM performance drops significantly as context length grows and preference expression becomes more implicit, and that generalizing user preference understanding to unseen scenarios poses further challenges. RealPref and these findings provide a foundation for future research to develop user-aware LLM assistants that better adapt to individual needs.
AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a novel benchmark of 170 trajectories across 11 diverse task settings, including structured API workflows, incident management, and open-ended web/file tasks. Each trajectory is annotated with a critical failure step and a category from a grounded-theory derived, cross-domain failure taxonomy. To mitigate the human cost of failure attribution, we present AgentRx, an $\textit{automated diagnostic framework}$ that pinpoints the critical failure step in a failed agent trajectory. It synthesizes constraints, evaluates them step-by-step, and produces an auditable validation log of constraint violations with associated evidence; an LLM-based judge uses this log to localize the critical step and category. AgentRx improves step localization by 75% on average over prior work, while providing failure category attribution.
Shraddha Barke, Arnav Goyal, Alind Khare et al.· 0 citations
Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most existing ARL methods train a single set of parameters to support both reasoning and tool-use behaviors, implicitly assuming that joint training leads to improved overall agent performance. Despite its widespread adoption, this assumption has rarely been examined empirically. In this paper, we systematically examine this assumption by introducing Capability Effect Attribution (CEA), which provides quantitative evidence of interference between reasoning and tool-use behaviors. Through an in-depth analysis, we show that these two capabilities often induce misaligned gradient directions, leading to training interference that undermines the effectiveness of joint optimization and challenges the prevailing ARL paradigm. To address this issue, we propose Disentangled Action--Reasoning Tuning (DART), a simple and efficient framework that explicitly decouples parameter updates for reasoning and tool use via separate low-rank adaptation modules. With this simple change alone, DART outperforms all joint-optimization baselines and approaches the 2-Agent upper bound across thirteen benchmarks on retrieval-augmented QA and NL2SQL, further supporting our finding of capability interference under shared optimization.
Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and highly sensitive to design choices. Prior evaluations frequently conflate base model capabilities with experimental instantiation, obscuring whether outcomes reflect the model itself or the agent setup. We instead frame $\textbf{participant simulation as an agent-design problem}$ over full experimental protocols, where an agent is defined by a base model and a specification (e.g., participant attributes) that encodes behavioral assumptions. We introduce $\textit{HUMANSTUDY-BENCH}$, an open platform and execution engine designed for practitioners to develop and evaluate agents tailored to their target experimental settings. The platform reconstructs published human-subject experiments via a human-in-the-loop Filter--Extract--Execute--Evaluate pipeline that preserves the original stimuli, conditions, and statistical procedures end to end, while allowing practitioners to freely explore the agent design space. We introduce two complementary metrics that quantify agreement with humans on both the significance conclusion and the effect size, while accounting for finite-sample uncertainty in the human reference data. In collaboration with social scientists, we validate the platform on a suite of 12 foundational studies covering 6,000+ trials across individual cognition, strategic interaction, and social psychology
Xuan Liu, Haoyang Shang, Zizhang Liu et al.· 0 citations
Artificial Intelligence (AI) has been on the rise in many domains, including numerous safety-critical applications. However, for complex systems in the real world, defining the underlying environmental conditions in which the AI-based system must operate---the Operational Design Domain (ODD)---is extremely challenging. This often results in an incomplete description of the ODD, which contrasts with the requirements of many domains for certifying AI-based systems. Traditionally, the ODD is created in the early stages of the development process, drawing on sophisticated expert knowledge and related standards. This paper presents a novel method for defining the ODD a posteriori from previously collected data using a multidimensional kernel-based representation. This approach is validated through both synthetic benchmarks and a real-world aviation use case. Moreover, the paper defines similarity of two ODDs if they generate the same outputs up to Lebesgue-null input sets and proves convergence in volume of the calibrated representation under the stated assumptions. The novel, safety-by-design, deterministic kernel-based ODD representation is derived fully automatically, given documented assurance inputs, permutation-stable, bounded by construction, and, under affine-equivariant per-dimension normalization, invariant to the choice of units. Utilizing the proposed ODD representation supports future certification of data-driven, safety-critical AI-based systems.
Johann Maximilian Christensen, Elena Hoemann, Frank K\"oster et al.· 0 citations
