Robotic manipulation in real-world settings remains challenging, especially regarding robust generalization. Existing simulation platforms lack sufficient support for exploring how policies adapt to varied instructions and scenarios. Thus, they lag behind the growing interest in instruction-following foundation models like LLMs, whose adaptability is crucial yet remains underexplored in fair comparisons. To bridge this gap, we introduce GenManip, a realistic tabletop simulation platform tailored for policy generalization studies. It features an automatic pipeline via LLM-driven task-oriented scene graph to synthesize large-scale, diverse tasks using 10K annotated 3D object assets. To systematically assess generalization, we present GenManip-Bench, a benchmark of 200 scenarios refined via human-in-the-loop corrections. We evaluate two policy types: (1) modular manipulation systems integrating foundation models for perception, reasoning, and planning, and (2) end-to-end policies trained through scalable data collection. Results show that while data scaling benefits end-to-end methods, modular systems enhanced with foundation models generalize more effectively across diverse scenarios. We anticipate this platform to facilitate critical insights for advancing policy generalization in realistic conditions. Project Page: https://genmanip.axi404.top/.
Classical AI Planning techniques generate sequences of actions for complex tasks. However, they lack the ability to understand planning tasks when provided using natural language. The advent of Large Language Models (LLMs) has introduced novel capabilities in human-computer interaction. In the context of planning tasks, LLMs have shown to be particularly good in interpreting human intents among other uses. This paper introduces GenPlanX that integrates LLMs for natural language-based description of planning tasks, with a classical AI planning engine, alongside an execution and monitoring framework. We demonstrate the efficacy of GenPlanX in assisting users with office-related tasks, highlighting its potential to streamline workflows and enhance productivity through seamless human-AI collaboration.
Human spatiotemporal behavior simulation is critical for urban planning research, yet traditional rule-based and statistical approaches suffer from high computational costs, limited generalizability, and poor scalability. While large language models (LLMs) show promise as "world simulators," they face challenges in spatiotemporal reasoning including limited spatial cognition, lack of physical constraint understanding, and group homogenization tendencies. This paper introduces a framework integrating chain-of-thought (CoT) reasoning with Model Context Protocol (MCP) to enhance LLMs' capability in simulating spatiotemporal behaviors that correspond with validation data patterns. The methodology combines human-like progressive reasoning through a five-stage cognitive framework with comprehensive data processing via six specialized MCP tool categories: temporal management, spatial navigation, environmental perception, personal memory, social collaboration, and experience evaluation. Experiments in Shanghai's Lujiazui district validate the framework's effectiveness across 1,000 generated samples. Results demonstrate high similarity with real mobile signaling data, achieving generation quality scores of 7.86 to 8.36 across different base models. Parallel processing experiments show efficiency improvements, with generation times decreasing from 1.30 to 0.17 minutes per sample when scaling from 2 to 12 processes. This work contributes to integrating CoT reasoning with MCP for urban behavior modeling, advancing LLMs applications in urban computing and providing a practical approach for synthetic mobility data generation. The framework offers a foundation for smart city planning, transportation forecasting, and participatory urban design applications.
We introduce LogiPlan, a novel benchmark designed to evaluate the capabilities of large language models (LLMs) in logical planning and reasoning over complex relational structures. Logical relational reasoning is important for applications that may rely on LLMs to generate and query structured graphs of relations such as network infrastructure, knowledge bases, or business process schema. Our framework allows for dynamic variation of task complexity by controlling the number of objects, relations, and the minimum depth of relational chains, providing a fine-grained assessment of model performance across difficulty levels. LogiPlan encompasses three complementary tasks: (1) Plan Generation, where models must construct valid directed relational graphs meeting specified structural constraints; (2) Consistency Detection, testing models' ability to identify inconsistencies in relational structures; and (3) Comparison Question, evaluating models' capacity to determine the validity of queried relationships within a given graph. Additionally, we assess models' self-correction capabilities by prompting them to verify and refine their initial solutions. We evaluate state-of-the-art models including DeepSeek R1, Gemini 2.0 Pro, Gemini 2 Flash Thinking, GPT-4.5, GPT-4o, Llama 3.1 405B, O3-mini, O1, and Claude 3.7 Sonnet across these tasks, revealing significant performance gaps that correlate with model scale and architecture. Our analysis demonstrates that while recent reasoning-enhanced models show promising results on simpler instances, they struggle with more complex configurations requiring deeper logical planning.
Static bug analyzers play a crucial role in ensuring software quality. However, existing analyzers for bug detection in large codebases often suffer from high false positive rates. This is primarily due to the limited capabilities of analyzers in path feasibility validation with multiple conditional branches and complex data dependencies. While current LLM-based approaches attempt to address this issue, their effectiveness remains limited due to insufficient constraint cascade analysis and scalability challenges in large projects. To address this challenge, we propose an iterative path feasibility analysis framework LLM4PFA. By leveraging LLM agent based targeted constraint reasoning, and key context-aware analysis driven by agent planning, LLM4PFA effectively enhances complex inter-procedural path feasibility analysis for minimizing false positives in static bug detection. Evaluation results show that LLM4PFA precisely filters out 72% to 96% false positives reported during static bug detection, significantly outperforming all the baselines by 41.1% - 105.7% improvements; meanwhile LLM4PFA only misses 3 real bugs of 45 true positives.
Recent breakthroughs in Large Language Models (LLMs) have led to a qualitative leap in artificial intelligence' s performance on reasoning tasks, particularly demonstrating remarkable capabilities in mathematical, symbolic, and commonsense reasoning. However, as a critical component of advanced human cognition, strategic reasoning, i.e., the ability to assess multi-agent behaviors in dynamic environments, formulate action plans, and adapt strategies, has yet to be systematically evaluated or modeled. To address this gap, this paper introduces WGSR-Bench, the first strategy reasoning benchmark for LLMs using wargame as its evaluation environment. Wargame, a quintessential high-complexity strategic scenario, integrates environmental uncertainty, adversarial dynamics, and non-unique strategic choices, making it an effective testbed for assessing LLMs' capabilities in multi-agent decision-making, intent inference, and counterfactual reasoning. WGSR-Bench designs test samples around three core tasks, i.e., Environmental situation awareness, Opponent risk modeling and Policy generation, which serve as the core S-POE architecture, to systematically assess main abilities of strategic reasoning. Finally, an LLM-based wargame agent is designed to integrate these parts for a comprehensive strategy reasoning assessment. With WGSR-Bench, we hope to assess the strengths and limitations of state-of-the-art LLMs in game-theoretic strategic reasoning and to advance research in large model-driven strategic intelligence.
Story generation has been a prominent application of Large Language Models (LLMs). However, understanding LLMs' ability to produce high-quality stories remains limited due to challenges in automatic evaluation methods and the high cost and subjectivity of manual evaluation. Computational narratology offers valuable insights into what constitutes a good story, which has been applied in the symbolic narrative planning approach to story generation. This work aims to deepen the understanding of LLMs' story generation capabilities by using them to solve narrative planning problems. We present a benchmark for evaluating LLMs on narrative planning based on literature examples, focusing on causal soundness, character intentionality, and dramatic conflict. Our experiments show that GPT-4 tier LLMs can generate causally sound stories at small scales, but planning with character intentionality and dramatic conflict remains challenging, requiring LLMs trained with reinforcement learning for complex reasoning. The results offer insights on the scale of stories that LLMs can generate while maintaining quality from different aspects. Our findings also highlight interesting problem solving behaviors and shed lights on challenges and considerations for applying LLM narrative planning in game environments.
Artificial intelligence is transforming precision agriculture, offering farmers new tools to streamline their daily operations. While these technological advances promise increased efficiency, they often introduce additional complexity and steep learning curves that are particularly challenging for non-technical users who must balance tech adoption with existing workloads. In this paper, we present a natural language (NL) robotic mission planner that enables non-specialists to control heterogeneous robots through a common interface. By leveraging large language models (LLMs) and predefined primitives, our architecture seamlessly translates human language into intermediate descriptions that can be executed by different robotic platforms. With this system, users can formulate complex agricultural missions without writing any code. In the work presented in this paper, we extend our previous system tailored for wheeled robot mission planning through a new class of experiments involving robotic manipulation and computer vision tasks. Our results demonstrate that the architecture is both general enough to support a diverse set of robots and powerful enough to execute complex mission requests. This work represents a significant step toward making robotic automation in precision agriculture more accessible to non-technical users.
Robotics and artificial intelligence hold significant potential for advancing precision agriculture. While robotic systems have been successfully deployed for various tasks, adapting them to perform diverse missions remains challenging, particularly because end users often lack technical expertise. In this paper, we present an end-to-end system that leverages large language models (LLMs), specifically ChatGPT, to enable users to assign complex data collection tasks to autonomous robots using natural language instructions. To enhance reusability, mission plans are encoded using an existing IEEE task specification standard, and are executed on robots via ROS2 nodes that bridge high-level mission descriptions with existing ROS libraries. Through extensive experiments, we highlight the strengths and limitations of LLMs in this context, particularly regarding spatial reasoning and solving complex routing challenges, and show how our proposed implementation overcomes them.
Monitoring Machine Learning (ML) models in production environments is crucial, yet traditional approaches often yield verbose, low-interpretability outputs that hinder effective decision-making. We propose a cognitive architecture for ML monitoring that applies feature engineering principles to agents based on Large Language Models (LLMs), significantly enhancing the interpretability of monitoring outputs. Central to our approach is a Decision Procedure module that simulates feature engineering through three key steps: Refactor, Break Down, and Compile. The Refactor step improves data representation to better capture feature semantics, allowing the LLM to focus on salient aspects of the monitoring data while reducing noise and irrelevant information. Break Down decomposes complex information for detailed analysis, and Compile integrates sub-insights into clear, interpretable outputs. This process leads to a more deterministic planning approach, reducing dependence on LLM-generated planning, which can sometimes be inconsistent and overly general. The combination of feature engineering-driven planning and selective LLM utilization results in a robust decision support system, capable of providing highly interpretable and actionable insights. Experiments using multiple LLMs demonstrate the efficacy of our approach, achieving significantly higher accuracy compared to various baselines across several domains.
Large Language Models (LLMs) have experienced great advancements in the last year resulting in an increase of these models in several fields to face natural language tasks. The integration of these models in robotics can also help to improve several aspects such as human-robot interaction, navigation, planning and decision-making. Therefore, this paper introduces llama\_ros, a tool designed to integrate quantized Large Language Models (LLMs) into robotic systems using ROS 2. Leveraging llama.cpp, a highly optimized runtime engine, llama\_ros enables the efficient execution of quantized LLMs as edge artificial intelligence (AI) in robotics systems with resource-constrained environments, addressing the challenges of computational efficiency and memory limitations. By deploying quantized LLMs, llama\_ros empowers robots to leverage the natural language understanding and generation for enhanced decision-making and interaction which can be paired with prompt engineering, knowledge graphs, ontologies or other tools to improve the capabilities of autonomous robots. Additionally, this paper provides insights into some use cases of using llama\_ros for planning and explainability in robotics.
Single-cell omics technologies have transformed our understanding of cellular diversity by enabling high-resolution profiling of individual cells. However, the unprecedented scale and heterogeneity of these datasets demand robust frameworks for data integration and annotation. The Cell Ontology (CL) has emerged as a pivotal resource for achieving FAIR (Findable, Accessible, Interoperable, and Reusable) data principles by providing standardized, species-agnostic terms for canonical cell types - forming a core component of a wide range of platforms and tools. In this paper, we describe the wide variety of uses of CL in these platforms and tools and detail ongoing work to improve and extend CL content including the addition of transcriptomically defined types, working closely with major atlasing efforts including the Human Cell Atlas and the Brain Initiative Cell Atlas Network to support their needs. We cover the challenges and future plans for harmonising classical and transcriptomic cell type definitions, integrating markers and using Large Language Models (LLMs) to improve content and efficiency of CL workflows.
Large Language Models (LLMs) are increasingly capable but often require significant guidance or extensive interaction history to perform effectively in complex, interactive environments. Existing methods may struggle with adapting to new information or efficiently utilizing past experiences for multi-step reasoning without fine-tuning. We introduce a novel LLM agent framework that enhances planning capabilities through in-context learning, facilitated by atomic fact augmentation and a recursive lookahead search. Our agent learns to extract task-critical ``atomic facts'' from its interaction trajectories. These facts dynamically augment the prompts provided to LLM-based components responsible for action proposal, latent world model simulation, and state-value estimation. Planning is performed via a depth-limited lookahead search, where the LLM simulates potential trajectories and evaluates their outcomes, guided by the accumulated facts and interaction history. This approach allows the agent to improve its understanding and decision-making online, leveraging its experience to refine its behavior without weight updates. We provide a theoretical motivation linking performance to the quality of fact-based abstraction and LLM simulation accuracy. Empirically, our agent demonstrates improved performance and adaptability on challenging interactive tasks, achieving more optimal behavior as it accumulates experience, showcased in tasks such as TextFrozenLake and ALFWorld.
How well do AI systems perform in algorithm engineering for hard optimization problems in domains such as package-delivery routing, crew scheduling, factory production planning, and power-grid balancing? We introduce ALE-Bench, a new benchmark for evaluating AI systems on score-based algorithmic programming contests. Drawing on real tasks from the AtCoder Heuristic Contests, ALE-Bench presents optimization problems that are computationally hard and admit no known exact solution. Unlike short-duration, pass/fail coding benchmarks, ALE-Bench encourages iterative solution refinement over long time horizons. Our software framework supports interactive agent architectures that leverage test-run feedback and visualizations. Our evaluation of frontier LLMs revealed that while they demonstrate high performance on specific problems, a notable gap remains compared to humans in terms of consistency across problems and long-horizon problem-solving capabilities. This highlights the need for this benchmark to foster future AI advancements.
Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning. However, these VLM-based approaches remain limited in their support for diverse embodiment types. In this work, we introduce VIKI-Bench, the first hierarchical benchmark tailored for embodied multi-agent cooperation, featuring three structured levels: agent activation, task planning, and trajectory perception. VIKI-Bench includes diverse robot embodiments, multi-view visual observations, and structured supervision signals to evaluate reasoning grounded in visual inputs. To demonstrate the utility of VIKI-Bench, we propose VIKI-R, a two-stage framework that fine-tunes a pretrained vision-language model (VLM) using Chain-of-Thought annotated demonstrations, followed by reinforcement learning under multi-level reward signals. Our extensive experiments show that VIKI-R significantly outperforms baselines method across all task levels. Furthermore, we show that reinforcement learning enables the emergence of compositional cooperation patterns among heterogeneous agents. Together, VIKI-Bench and VIKI-R offer a unified testbed and method for advancing multi-agent, visual-driven cooperation in embodied AI systems.
Leveraging multiple Large Language Models(LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints, we present the Agentic Neural Network(ANN), a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. In this design, each agent operates as a node, and each layer forms a cooperative "team" focused on a specific subtask. Agentic Neural Network follows a two-phase optimization strategy: (1) Forward Phase-Drawing inspiration from neural network forward passes, tasks are dynamically decomposed into subtasks, and cooperative agent teams with suitable aggregation methods are constructed layer by layer. (2) Backward Phase-Mirroring backpropagation, we refine both global and local collaboration through iterative feedback, allowing agents to self-evolve their roles, prompts, and coordination. This neuro-symbolic approach enables ANN to create new or specialized agent teams post-training, delivering notable gains in accuracy and adaptability. Across four benchmark datasets, ANN surpasses leading multi-agent baselines under the same configurations, showing consistent performance improvements. Our findings indicate that ANN provides a scalable, data-driven framework for multi-agent systems, combining the collaborative capabilities of LLMs with the efficiency and flexibility of neural network principles. We plan to open-source the entire framework.
The rapid growth of the low-altitude economy has driven the widespread adoption of unmanned aerial vehicles (UAVs). This growing deployment presents new challenges for UAV trajectory planning in complex urban environments. However, existing studies often overlook key factors, such as urban airspace constraints and economic efficiency, which are essential in low-altitude economy contexts. Deep reinforcement learning (DRL) is regarded as a promising solution to these issues, while its practical adoption remains limited by low learning efficiency. To overcome this limitation, we propose a novel UAV trajectory planning framework that combines DRL with large language model (LLM) reasoning to enable safe, compliant, and economically viable path planning. Experimental results demonstrate that our method significantly outperforms existing baselines across multiple metrics, including data collection rate, collision avoidance, successful landing, regulatory compliance, and energy efficiency. These results validate the effectiveness of our approach in addressing UAV trajectory planning key challenges under constraints of the low-altitude economy networking.
The rise of large language models (LLMs) has created new possibilities for digital twins in healthcare. However, the deployment of such systems in consumer health contexts raises significant concerns related to hallucination, bias, lack of transparency, and ethical misuse. In response to recommendations from health authorities such as the World Health Organization (WHO), we propose Responsible Health Twin (RHealthTwin), a principled framework for building and governing AI-powered digital twins for well-being assistance. RHealthTwin processes multimodal inputs that guide a health-focused LLM to produce safe, relevant, and explainable responses. At the core of RHealthTwin is the Responsible Prompt Engine (RPE), which addresses the limitations of traditional LLM configuration. Conventionally, users input unstructured prompt and the system instruction to configure the LLM, which increases the risk of hallucination. In contrast, RPE extracts predefined slots dynamically to structure both inputs. This guides the language model to generate responses that are context aware, personalized, fair, reliable, and explainable for well-being assistance. The framework further adapts over time through a feedback loop that updates the prompt structure based on user satisfaction. We evaluate RHealthTwin across four consumer health domains including mental support, symptom triage, nutrition planning, and activity coaching. RPE achieves state-of-the-art results with BLEU = 0.41, ROUGE-L = 0.63, and BERTScore = 0.89 on benchmark datasets. Also, we achieve over 90% in ethical compliance and instruction-following metrics using LLM-as-judge evaluation, outperforming baseline strategies. We envision RHealthTwin as a forward-looking foundation for responsible LLM-based applications in health and well-being.
Large language models (LLMs) can face factual limitations when responding to
time-sensitive queries about recent events that arise after their knowledge
thresholds in the training corpus. Existing search-augmented approaches fall
into two categories, each with distinct limitations: multi-agent search
frameworks incur substantial computational overhead by separating search
planning and response synthesis across multiple LLMs, while single-LLM
tool-calling methods restrict themselves to sequential planned, single-query
searches from sole search sources. We present Reasoning-Search (R-Search), a
single-LLM search framework that unifies multi-step planning, multi-source
search execution, and answer synthesis within one coherent inference process.
Innovatively, it structure the output into four explicitly defined components,
including reasoning steps that guide the search process (
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific triggers in their inputs or environments. To address this pressing risk, we present ReAgent, a novel defense against a range of backdoor attacks on LLM-based agents. Intuitively, backdoor attacks often result in inconsistencies among the user's instruction, the agent's planning, and its execution. Drawing on this insight, ReAgent employs a two-level approach to detect potential backdoors. At the execution level, ReAgent verifies consistency between the agent's thoughts and actions; at the planning level, ReAgent leverages the agent's capability to reconstruct the instruction based on its thought trajectory, checking for consistency between the reconstructed instruction and the user's instruction. Extensive evaluation demonstrates ReAgent's effectiveness against various backdoor attacks across tasks. For instance, ReAgent reduces the attack success rate by up to 90\% in database operation tasks, outperforming existing defenses by large margins. This work reveals the potential of utilizing compromised agents themselves to mitigate backdoor risks.
Multi-agent frameworks can substantially boost the reasoning power of large language models (LLMs), but they typically incur heavy computational costs and lack convergence guarantees. To overcome these challenges, we recast multi-LLM coordination as an incomplete-information game and seek a Bayesian Nash equilibrium (BNE), in which each agent optimally responds to its probabilistic beliefs about the strategies of others. We introduce Efficient Coordination via Nash Equilibrium (ECON), a hierarchical reinforcement-learning paradigm that marries distributed reasoning with centralized final output. Under ECON, each LLM independently selects responses that maximize its expected reward, conditioned on its beliefs about co-agents, without requiring costly inter-agent exchanges. We mathematically prove that ECON attains a markedly tighter regret bound than non-equilibrium multi-agent schemes. Empirically, ECON outperforms existing multi-LLM approaches by 11.2% on average across six benchmarks spanning complex reasoning and planning tasks. Further experiments demonstrate ECON's ability to flexibly incorporate additional models, confirming its scalability and paving the way toward larger, more powerful multi-LLM ensembles. The code is publicly available at: https://github.com/tmlr-group/ECON.
We introduce EconWebArena, a benchmark for evaluating autonomous agents on complex, multimodal economic tasks in realistic web environments. The benchmark comprises 360 curated tasks from 82 authoritative websites spanning domains such as macroeconomics, labor, finance, trade, and public policy. Each task challenges agents to navigate live websites, interpret structured and visual content, interact with real interfaces, and extract precise, time-sensitive data through multi-step workflows. We construct the benchmark by prompting multiple large language models (LLMs) to generate candidate tasks, followed by rigorous human curation to ensure clarity, feasibility, and source reliability. Unlike prior work, EconWebArena emphasizes fidelity to authoritative data sources and the need for grounded web-based economic reasoning. We evaluate a diverse set of state-of-the-art multimodal LLMs as web agents, analyze failure cases, and conduct ablation studies to assess the impact of visual grounding, plan-based reasoning, and interaction design. Our results reveal substantial performance gaps and highlight persistent challenges in grounding, navigation, and multimodal understanding, positioning EconWebArena as a rigorous testbed for economic web intelligence.
Large Language Models (LLMs) demonstrate impressive general-purpose reasoning and problem-solving abilities. However, they struggle with executing complex, long-horizon workflows that demand strict adherence to Standard Operating Procedures (SOPs), a critical requirement for real-world industrial automation. Despite this need, there is a lack of public benchmarks that reflect the complexity, structure, and domain-specific nuances of SOPs. To address this, we present three main contributions. First, we introduce a synthetic data generation framework to create realistic, industry-grade SOPs that rigorously test the planning, reasoning, and tool-use capabilities of LLM-based agents. Second, using this framework, we develop SOP-Bench, a benchmark of over 1,800 tasks across 10 industrial domains, each with APIs, tool interfaces, and human-validated test cases. Third, we evaluate two prominent agent architectures: Function-Calling and ReAct Agents, on SOP-Bench, observing average success rates of only 27% and 48%, respectively. Remarkably, when the tool registry is much larger than necessary, agents invoke incorrect tools nearly 100% of the time. These findings underscore a substantial gap between current agentic capabilities of LLMs and the demands of automating real-world SOPs. Performance varies significantly by task and domain, highlighting the need for domain-specific benchmarking and architectural choices before deployment. SOP-Bench is publicly available at http://sop-bench.s3-website-us-west-2.amazonaws.com/. We also release the prompts underpinning the data generation framework to support new domain-specific SOP benchmarks. We invite the community to extend SOP-Bench with SOPs from their industrial domains.
The emergence of capable large language model (LLM) based agents necessitates memory architectures that transcend mere data storage, enabling continuous learning, nuanced reasoning, and dynamic adaptation. Current memory systems often grapple with fundamental limitations in structural flexibility, temporal awareness, and the ability to synthesize higher-level insights from raw interaction data. This paper introduces Cognitive Weave, a novel memory framework centered around a multi-layered spatio-temporal resonance graph (STRG). This graph manages information as semantically rich insight particles (IPs), which are dynamically enriched with resonance keys, signifiers, and situational imprints via a dedicated semantic oracle interface (SOI). These IPs are interconnected through typed relational strands, forming an evolving knowledge tapestry. A key component of Cognitive Weave is the cognitive refinement process, an autonomous mechanism that includes the synthesis of insight aggregates (IAs) condensed, higher-level knowledge structures derived from identified clusters of related IPs. We present comprehensive experimental results demonstrating Cognitive Weave's marked enhancement over existing approaches in long-horizon planning tasks, evolving question-answering scenarios, and multi-session dialogue coherence. The system achieves a notable 34% average improvement in task completion rates and a 42% reduction in mean query latency when compared to state-of-the-art baselines. Furthermore, this paper explores the ethical considerations inherent in such advanced memory systems, discusses the implications for long-term memory in LLMs, and outlines promising future research trajectories.
While Large Language Models (LLMs) have demonstrated significant advancements in reasoning and agent-based problem-solving, current evaluation methodologies fail to adequately assess their capabilities: existing benchmarks either rely on closed-ended questions prone to saturation and memorization, or subjective comparisons that lack consistency and rigor. In this work, we introduce HeuriGym, an agentic framework designed for evaluating heuristic algorithms generated by LLMs for combinatorial optimization problems, characterized by clearly defined objectives and expansive solution spaces. HeuriGym empowers LLMs to propose heuristics, receive evaluative feedback via code execution, and iteratively refine their solutions. We evaluate nine state-of-the-art models on nine problems across domains such as computer systems, logistics, and biology, exposing persistent limitations in tool use, planning, and adaptive reasoning. To quantify performance, we propose the Quality-Yield Index (QYI), a metric that captures both solution pass rate and quality. Even top models like GPT-o4-mini-high and Gemini-2.5-Pro attain QYI scores of only 0.6, well below the expert baseline of 1. Our open-source benchmark aims to guide the development of LLMs toward more effective and realistic problem-solving in scientific and engineering domains.
The advancement in large language models (LLMs) and large vision models has fueled the rapid progress in multi-modal visual-text reasoning capabilities. However, existing vision-language models (VLMs) to date suffer from generalization performance. Inspired by recent development in LLMs for visual reasoning, this paper presents VLAgent, an AI system that can create a step-by-step visual reasoning plan with an easy-to-understand script and execute each step of the plan in real time by integrating planning script with execution verifications via an automated process supported by VLAgent. In the task planning phase, VLAgent fine-tunes an LLM through in-context learning to generate a step-by-step planner for each user-submitted text-visual reasoning task. During the plan execution phase, VLAgent progressively refines the composition of neuro-symbolic executable modules to generate high-confidence reasoning results. VLAgent has three unique design characteristics: First, we improve the quality of plan generation through in-context learning, improving logic reasoning by reducing erroneous logic steps, incorrect programs, and LLM hallucinations. Second, we design a syntax-semantics parser to identify and correct additional logic errors of the LLM-generated planning script prior to launching the plan executor. Finally, we employ the ensemble method to improve the generalization performance of our step-executor. Extensive experiments with four visual reasoning benchmarks (GQA, MME, NLVR2, VQAv2) show that VLAgent achieves significant performance enhancement for multimodal text-visual reasoning applications, compared to the exiting representative VLMs and LLM based visual composition approaches like ViperGPT and VisProg, thanks to the novel optimization modules of VLAgent back-engine (SS-Parser, Plan Repairer, Output Verifiers). Code and data will be made available upon paper acceptance.
Query rewrite transforms SQL queries into semantically equivalent forms that run more efficiently. Existing approaches mainly rely on predefined rewrite rules, but they handle a limited subset of queries and can cause performance regressions. This limitation stems from three challenges of rule-based query rewrite: (1) it is hard to discover and verify new rules, (2) fixed rewrite rules do not generalize to new query patterns, and (3) some rewrite techniques cannot be expressed as fixed rules. Motivated by the fact that human experts exhibit significantly better rewrite ability but suffer from scalability, and Large Language Models (LLMs) have demonstrated nearly human-level semantic and reasoning abilities, we propose a new approach of using LLMs to rewrite SQL queries beyond rules. Due to the hallucination problems in LLMs, directly applying LLMs often leads to nonequivalent and suboptimal queries. To address this issue, we propose QUITE (query rewrite), a training-free and feedback-aware system based on LLM agents that rewrites SQL queries into semantically equivalent forms with significantly better performance, covering a broader range of query patterns and rewrite strategies compared to rule-based methods. Firstly, we design a multi-agent framework controlled by a finite state machine (FSM) to equip LLMs with the ability to use external tools and enhance the rewrite process with real-time database feedback. Secondly, we develop a rewrite middleware to enhance the ability of LLMs to generate optimized query equivalents. Finally, we employ a novel hint injection technique to improve execution plans for rewritten queries. Extensive experiments show that QUITE reduces query execution time by up to 35.8% over state-of-the-art approaches and produces 24.1% more rewrites than prior methods, covering query cases that earlier systems did not handle.
The dual use nature of Large Language Models (LLMs) presents a growing challenge in cybersecurity. While LLM enhances automation and reasoning for defenders, they also introduce new risks, particularly their potential to be misused for generating evasive, AI crafted malware. Despite this emerging threat, the research community currently lacks controlled and extensible tools that can simulate such behavior for testing and defense preparation. We present MalGEN, a multi agent framework that simulates coordinated adversarial behavior to generate diverse, activity driven malware samples. The agents work collaboratively to emulate attacker workflows, including payload planning, capability selection, and evasion strategies, within a controlled environment built for ethical and defensive research. Using MalGEN, we synthesized ten novel malware samples and evaluated them against leading antivirus and behavioral detection engines. Several samples exhibited stealthy and evasive characteristics that bypassed current defenses, validating MalGEN's ability to model sophisticated and new threats. By transforming the threat of LLM misuse into an opportunity for proactive defense, MalGEN offers a valuable framework for evaluating and strengthening cybersecurity systems. The framework addresses data scarcity, enables rigorous testing, and supports the development of resilient and future ready detection strategies.
Large language models (LLMs) have recently demonstrated promising capabilities in chemistry tasks while still facing challenges due to outdated pretraining knowledge and the difficulty of incorporating specialized chemical expertise. To address these issues, we propose an LLM-based agent that synergistically integrates 137 external chemical tools created ranging from basic information retrieval to complex reaction predictions, and a dataset curation pipeline to generate the dataset ChemToolBench that facilitates both effective tool selection and precise parameter filling during fine-tuning and evaluation. We introduce a Hierarchical Evolutionary Monte Carlo Tree Search (HE-MCTS) framework, enabling independent optimization of tool planning and execution. By leveraging self-generated data, our approach supports step-level fine-tuning (FT) of the policy model and training task-adaptive PRM and ORM that surpass GPT-4o. Experimental evaluations demonstrate that our approach significantly improves performance in Chemistry QA and discovery tasks, offering a robust solution to integrate specialized tools with LLMs for advanced chemical applications. All datasets and code are available at https://github.com/AI4Chem/ChemistryAgent .
Recent advances in large language model (LLM) reasoning have shown that sophisticated behaviors such as planning and self-reflection can emerge through reinforcement learning (RL). However, despite these successes, RL in its current form remains insufficient to induce capabilities that exceed the limitations of the base model, as it is primarily optimized based on existing knowledge of the model rather than facilitating the acquisition of new information. To address this limitation, we employ supervised fine-tuning (SFT) to learn what RL cannot, which enables the incorporation of new knowledge and reasoning patterns by leveraging high-quality demonstration data. We analyze the training dynamics of RL and SFT for LLM reasoning and find that RL excels at maintaining and improving performance on questions within the model's original capabilities, while SFT is more effective at enabling progress on questions beyond the current scope of the model. Motivated by the complementary strengths of RL and SFT, we introduce a novel training approach, \textbf{ReLIFT} (\textbf{Re}inforcement \textbf{L}earning \textbf{I}nterleaved with Online \textbf{F}ine-\textbf{T}uning). In ReLIFT, the model is primarily trained using RL, but when it encounters challenging questions, high-quality solutions are collected for fine-tuning, and the training process alternates between RL and fine-tuning to enhance the model's reasoning abilities. ReLIFT achieves an average improvement of over +5.2 points across five competition-level benchmarks and one out-of-distribution benchmark compared to other zero-RL models. Furthermore, we demonstrate that ReLIFT outperforms both RL and SFT while using only 13\% of the detailed demonstration data, highlighting its scalability. These results provide compelling evidence that ReLIFT overcomes the fundamental limitations of RL and underscores the significant potential.