Tool use in stateful environments presents unique challenges for large language models (LLMs), where existing test-time compute strategies relying on repeated trials in the environment are impractical. We propose dynamics modelling (DyMo), a method that augments LLMs with a state prediction capability alongside function calling during post-training. This enables LLMs to predict the future states of their actions through an internal environment model. On the Berkeley Function Calling Leaderboard V2, DyMo improves success rates and significantly reduces hallucinations. We further integrate the internal environment model into self-verification sampling (SVS), and show that this substantially improves pass^k over number of trials k, and allows the model to refuse unreliable outputs. Together, DyMo and SVS greatly enhance the effectiveness and reliability of LLMs for tool use. We believe this work charts a path towards scalable planning RL methods for LLM inference without repeatedly querying the oracle environment.
Task planning under uncertainty is essential for home-service robots operating in the real world. Tasks involve ambiguous human instructions, hidden or unknown object locations, and open-vocabulary object types, leading to significant open-ended uncertainty and a boundlessly large planning space. To address these challenges, we propose Tru-POMDP, a planner that combines structured belief generation using Large Language Models (LLMs) with principled POMDP planning. Tru-POMDP introduces a hierarchical Tree of Hypotheses (TOH), which systematically queries an LLM to construct high-quality particle beliefs over possible world states and human goals. We further formulate an open-ended POMDP model that enables rigorous Bayesian belief tracking and efficient belief-space planning over these LLM-generated hypotheses. Experiments on complex object rearrangement tasks across diverse kitchen environments show that Tru-POMDP significantly outperforms state-of-the-art LLM-based and LLM-tree-search hybrid planners, achieving higher success rates with significantly better plans, stronger robustness to ambiguity and occlusion, and greater planning efficiency.
Hybrid parallelism techniques are essential for efficiently training large language models (LLMs). Nevertheless, current automatic parallel planning frameworks often overlook the simultaneous consideration of node heterogeneity and dynamic network topology changes, limiting their effectiveness in practical applications. In this paper, we address these limitations by modeling heterogeneous nodes within dynamically changing network environments and leveraging simulation-based strategies to determine optimal parallel configurations. Our approach enables fine-grained workload allocation tailored for heterogeneous nodes and complex network scenarios, achieving performance competitive with state-of-the-art methods under regular and stable network conditions. Additionally, we introduce a strategy pruning technique to rapidly discard infeasible parallel configurations, substantially reducing the search space and accelerating the search process through parallel execution within the simulator. Preliminary evaluations confirm that our method notably enhances training performance on heterogeneous nodes and demonstrates improved adaptability in complex, dynamic scenarios such as cloud computing environments.
Large Language Models (LLMs) have become foundational to modern AI agent systems, enabling autonomous agents to reason and plan. In most existing systems, inter-agent communication relies primarily on natural language. While this design supports interpretability and human oversight, we argue that it introduces fundamental limitations in agent-to-agent coordination. The semantic space of natural language is structurally misaligned with the high-dimensional vector spaces in which LLMs operate, resulting in information loss and behavioral drift. Beyond surface-level inefficiencies, we highlight a deeper architectural limitation: current LLMs were not trained with the objective of supporting agentic behavior. As such, they lack mechanisms for modeling role continuity, task boundaries, and multi-agent dependencies. The standard next-token prediction paradigm fails to support the structural alignment required for robust, scalable agent coordination. Based on this, we argue that two core questions deserve careful examination: first, given that AI agents fundamentally operate in high-dimensional vector spaces, should they rely on a language system originally designed for human cognition as their communication medium? Second, should we consider developing a new model construction paradigm that builds models from the ground up to natively support structured communication, shared intentionality, and task alignment in multi-role, multi-agent environments? This paper calls for a reconsideration not only of how agents should communicate, but also of what it fundamentally means to train a model that natively supports multi-agent coordination and communication.
Despite significant advances in Large Language Models (LLMs), planning tasks still present challenges for LLM-based agents. Existing planning methods face two key limitations: heavy constraints and cascading errors. To address these limitations, we propose a novel parallel planning paradigm, which Decomposes, Plans for subtasks in Parallel, and Merges subplans into a final plan (DPPM). Specifically, DPPM decomposes the complex task based on constraints into subtasks, generates the subplan for each subtask in parallel, and merges them into a global plan. In addition, our approach incorporates a verification and refinement module, enabling error correction and conflict resolution. Experimental results demonstrate that DPPM significantly outperforms existing methods in travel planning tasks.
While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous researches integrate external, reliable tools to alleviate logical inconsistencies and hallucinations in LLMs' problem-solving processes. However, we argue that the root challenge is more profound: LLMs lack the complex thinking paradigms (\ie, computational thinking) during reasoning. In this paper, we propose Computational Thinking Model (CTM), a novel framework that incorporates computational thinking paradigms into LLMs. This framework enables LLMs to reformulate complex problems through decomposition, abstraction, reduction, and simulation, among other techniques. Specifically, live code execution is seamlessly integrated into the reasoning process, allowing CTM to think by computing. CTM directly instills computational thinking objectives into LLMs through tailored reinforcement learning rewards, which encourages problem simplification, modular planning, and iterative verification. We conduct extensive evaluations on multiple code generation and mathematical benchmarks. The results demonstrate that CTM outperforms conventional reasoning models and tool-augmented baselines in terms of accuracy, interpretability, and generalizability. We hope this study offers valuable insights for AI reasoning, where LLMs can transform problems into robust, verifiable, and scalable computational workflows, much like computer scientists do.
A public safety Unmanned Aerial Vehicle (UAV) enhances situational awareness in emergency response. Its agility and ability to optimize mobility and establish Line-of-Sight (LoS) communication make it increasingly vital for managing emergencies such as disaster response, search and rescue, and wildfire monitoring. While Deep Reinforcement Learning (DRL) has been applied to optimize UAV navigation and control, its high training complexity, low sample efficiency, and simulation-to-reality gap limit its practicality in public safety. Recent advances in Large Language Models (LLMs) offer a compelling alternative. With strong reasoning and generalization capabilities, LLMs can adapt to new tasks through In-Context Learning (ICL), which enables task adaptation via natural language prompts and example-based guidance, without retraining. Deploying LLMs at the network edge, rather than in the cloud, further reduces latency and preserves data privacy, thereby making them suitable for real-time, mission-critical public safety UAVs. This paper proposes the integration of LLM-enabled ICL with public safety UAV to address the key functions, such as path planning and velocity control, in the context of emergency response. We present a case study on data collection scheduling where the LLM-enabled ICL framework can significantly reduce packet loss compared to conventional approaches, while also mitigating potential jailbreaking vulnerabilities. Finally, we discuss LLM optimizers and specify future research directions. The ICL framework enables adaptive, context-aware decision-making for public safety UAV, thus offering a lightweight and efficient solution for enhancing UAV autonomy and responsiveness in emergencies.
Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scenes either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or 'table'), require masked diffusion for editing, ignore room boundaries, or rely on floor plan renderings that fail to capture complex layouts. In contrast, LLM-based methods enable richer semantics via natural language (e.g., 'modern studio with light wood furniture') but do not support editing, remain limited to rectangular layouts or rely on weak spatial reasoning from implicit world models. We introduce ReSpace, a generative framework for text-driven 3D indoor scene synthesis and editing using autoregressive language models. Our approach features a compact structured scene representation with explicit room boundaries that frames scene editing as a next-token prediction task. We leverage a dual-stage training approach combining supervised fine-tuning and preference alignment, enabling a specially trained language model for object addition that accounts for user instructions, spatial geometry, object semantics, and scene-level composition. For scene editing, we employ a zero-shot LLM to handle object removal and prompts for addition. We further introduce a novel voxelization-based evaluation that captures fine-grained geometry beyond 3D bounding boxes. Experimental results surpass state-of-the-art on object addition while maintaining competitive results on full scene synthesis.
Visualizations play a crucial part in effective communication of concepts and information. Recent advances in reasoning and retrieval augmented generation have enabled Large Language Models (LLMs) to perform deep research and generate comprehensive reports. Despite its progress, existing deep research frameworks primarily focus on generating text-only content, leaving the automated generation of interleaved texts and visualizations underexplored. This novel task poses key challenges in designing informative visualizations and effectively integrating them with text reports. To address these challenges, we propose Formal Description of Visualization (FDV), a structured textual representation of charts that enables LLMs to learn from and generate diverse, high-quality visualizations. Building on this representation, we introduce Multimodal DeepResearcher, an agentic framework that decomposes the task into four stages: (1) researching, (2) exemplar report textualization, (3) planning, and (4) multimodal report generation. For the evaluation of generated multimodal reports, we develop MultimodalReportBench, which contains 100 diverse topics served as inputs along with 5 dedicated metrics. Extensive experiments across models and evaluation methods demonstrate the effectiveness of Multimodal DeepResearcher. Notably, utilizing the same Claude 3.7 Sonnet model, Multimodal DeepResearcher achieves an 82\% overall win rate over the baseline method.
Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these conflict with operational goals. Failure to prioritize such principles indicates a potential basic control failure. This paper introduces a lightweight, interpretable benchmark methodology using a simple grid world to evaluate an LLM agent's ability to uphold a predefined, high-level safety principle (e.g., "never enter hazardous zones") when faced with conflicting lower-level task instructions. We probe whether the agent reliably prioritizes the inviolable directive, testing a foundational controllability aspect of LLMs. This pilot study demonstrates the methodology's feasibility, offers preliminary insights into agent behavior under principle conflict, and discusses how such benchmarks can contribute empirical evidence for assessing controllability. We argue that evaluating adherence to hierarchical principles is a crucial early step in understanding our capacity to build governable AI systems.
Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback. To address these issues, we present LAM SIMULATOR, a comprehensive framework designed for online exploration of agentic tasks with high-quality feedback. Our framework features a dynamic task query generator, an extensive collection of tools, and an interactive environment where Large Language Model (LLM) Agents can call tools and receive real-time feedback. This setup enables LLM Agents to explore and solve tasks autonomously, facilitating the discovery of multiple approaches to tackle any given task. The resulting action trajectory data are then used to create high-quality training datasets for LAMs. Our experiments on popular agentic benchmarks, ToolBench and CRMArena, highlight the effectiveness of LAM SIMULATOR: models trained with self-generated datasets using our framework achieve significant performance gains, up to a 49.3\% improvement over their original baselines. LAM SIMULATOR requires minimal human input during dataset creation, highlighting LAM SIMULATOR's efficiency and effectiveness in speeding up development of AI agents.
Large Language Model (LLM) agents have demonstrated impressive capabilities in handling complex interactive problems. Existing LLM agents mainly generate natural language plans to guide reasoning, which is verbose and inefficient. NL plans are also tailored to specific tasks and restrict agents' ability to generalize across similar tasks. To this end, we explore pseudocode-style plans (P-code Plan) to capture the structural logic of reasoning. We find that P-code Plan empowers LLM agents with stronger generalization ability and more efficiency. Inspired by this finding, we propose a pseudocode-style Planning Guided Preference Optimization method called PGPO for effective agent learning. With two planning-oriented rewards, PGPO further enhances LLM agents' ability to generate high-quality P-code Plans and subsequent reasoning. Experiments show that PGPO achieves superior performance on representative agent benchmarks and outperforms the current leading baselines. Analyses reveal the advantage of PGPO in reducing action errors and omissions during reasoning.
Reinforcement learning (RL) has driven breakthroughs in AI, from game-play to scientific discovery and AI alignment. However, its broader applicability remains limited by challenges such as low data efficiency and poor generalizability. Recent advances suggest that large language models, with their rich world knowledge and reasoning capabilities, could complement RL by enabling semantic state modeling and task-agnostic planning. In this work, we propose the Agentic Episodic Control (AEC), a novel architecture that integrates RL with LLMs to enhance decision-making. The AEC can leverage a large language model (LLM) to map the observations into language-grounded embeddings, which further can be stored in an episodic memory for rapid retrieval of high-value experiences. Simultaneously, a World-Graph working memory module is utilized to capture structured environmental dynamics in order to enhance relational reasoning. Furthermore, a lightweight critical state detector dynamically arbitrates between the episodic memory recall and the world-model-guided exploration. On the whole, by combining the trial-and-error learning scheme with LLM-derived semantic priors, the proposed AEC can improve both data efficiency and generalizability in reinforcement learning. In experiments on BabyAI-Text benchmark tasks, AEC demonstrates substantial improvements over existing baselines, especially on complex and generalization tasks like FindObj, where it outperforms the best baseline by up to 76%. The proposed AEC framework bridges the strengths of numeric reinforcement learning and symbolic reasoning, which provides a pathway toward more adaptable and sample-efficient agents.
The emergence of ChatGPT marked a transformative milestone for Artificial Intelligence (AI), showcasing the remarkable potential of Large Language Models (LLMs) to generate human-like text. This wave of innovation has revolutionized how we interact with technology, seamlessly integrating LLMs into everyday tasks such as vacation planning, email drafting, and content creation. While English-speaking users have significantly benefited from these advancements, the Arabic world faces distinct challenges in developing Arabic-specific LLMs. Arabic, one of the languages spoken most widely around the world, serves more than 422 million native speakers in 27 countries and is deeply rooted in a rich linguistic and cultural heritage. Developing Arabic LLMs (ALLMs) presents an unparalleled opportunity to bridge technological gaps and empower communities. The journey of ALLMs has been both fascinating and complex, evolving from rudimentary text processing systems to sophisticated AI-driven models. This article explores the trajectory of ALLMs, from their inception to the present day, highlighting the efforts to evaluate these models through benchmarks and public leaderboards. We also discuss the challenges and opportunities that ALLMs present for the Arab world.
Psychological support hotlines are critical for crisis intervention but face significant challenges due to rising demand. Large language models (LLMs) could support crisis assessments, yet their capabilities in emotionally sensitive contexts remain unclear. We introduce PsyCrisisBench, a benchmark of 540 annotated transcripts from the Hangzhou Psychological Assistance Hotline, assessing four tasks: mood status recognition, suicidal ideation detection, suicide plan identification, and risk assessment. We evaluated 64 LLMs across 15 families (e.g., GPT, Claude, Gemini, Llama, Qwen, DeepSeek) using zero-shot, few-shot, and fine-tuning paradigms. Performance was measured by F1-score, with statistical comparisons via Welch's t-tests. LLMs performed strongly on suicidal ideation detection (F1=0.880), suicide plan identification (F1=0.779), and risk assessment (F1=0.907), improved with few-shot and fine-tuning. Mood status recognition was more challenging (max F1=0.709), likely due to lost vocal cues and ambiguity. A fine-tuned 1.5B-parameter model (Qwen2.5-1.5B) surpassed larger models on mood and suicidal ideation. Open-source models like QwQ-32B performed comparably to closed-source on most tasks (p>0.3), though closed models retained an edge in mood detection (p=0.007). Performance scaled with size up to a point; quantization (AWQ) reduced GPU memory by 70% with minimal F1 degradation. LLMs show substantial promise in structured psychological crisis assessments, especially with fine-tuning. Mood recognition remains limited due to contextual complexity. The narrowing gap between open- and closed-source models, combined with efficient quantization, suggests feasible integration. PsyCrisisBench offers a robust evaluation framework to guide model development and ethical deployment in mental health.
Operations research (OR) is widely deployed to solve critical decision-making problems with complex objectives and constraints, impacting manufacturing, logistics, finance, and healthcare outcomes. While Large Language Models (LLMs) have shown promising results in various domains, their practical application in industry-relevant operations research (OR) problems presents significant challenges and opportunities. Preliminary industrial applications of LLMs for operations research face two critical deployment challenges: 1) Self-correction focuses on code syntax rather than mathematical accuracy, causing costly errors; 2) Complex expert selection creates unpredictable workflows that reduce transparency and increase maintenance costs, making them impractical for time-sensitive business applications. To address these business limitations, we introduce ORMind, a cognitive-inspired framework that enhances optimization through counterfactual reasoning. Our approach emulates human cognition, implementing an end-to-end workflow that systematically transforms requirements into mathematical models and executable solver code. It is currently being tested internally in Lenovo's AI Assistant, with plans to enhance optimization capabilities for both business and consumer customers. Experiments demonstrate that ORMind outperforms existing methods, achieving a 9.5\% improvement on the NL4Opt dataset and a 14.6\% improvement on the ComplexOR dataset.
Traditional Chinese Medicine (TCM) is a holistic medical system with millennia of accumulated clinical experience, playing a vital role in global healthcare-particularly across East Asia. However, the implicit reasoning, diverse textual forms, and lack of standardization in TCM pose major challenges for computational modeling and evaluation. Large Language Models (LLMs) have demonstrated remarkable potential in processing natural language across diverse domains, including general medicine. Yet, their systematic evaluation in the TCM domain remains underdeveloped. Existing benchmarks either focus narrowly on factual question answering or lack domain-specific tasks and clinical realism. To fill this gap, we introduce MTCMB-a Multi-Task Benchmark for Evaluating LLMs on TCM Knowledge, Reasoning, and Safety. Developed in collaboration with certified TCM experts, MTCMB comprises 12 sub-datasets spanning five major categories: knowledge QA, language understanding, diagnostic reasoning, prescription generation, and safety evaluation. The benchmark integrates real-world case records, national licensing exams, and classical texts, providing an authentic and comprehensive testbed for TCM-capable models. Preliminary results indicate that current LLMs perform well on foundational knowledge but fall short in clinical reasoning, prescription planning, and safety compliance. These findings highlight the urgent need for domain-aligned benchmarks like MTCMB to guide the development of more competent and trustworthy medical AI systems. All datasets, code, and evaluation tools are publicly available at: https://github.com/Wayyuanyuan/MTCMB.
Can AI effectively perform complex econometric analysis traditionally requiring human expertise? This paper evaluates an agentic AI's capability to master econometrics, focusing on empirical analysis performance. We develop an ``Econometrics AI Agent'' built on the open-source MetaGPT framework. This agent exhibits outstanding performance in: (1) planning econometric tasks strategically, (2) generating and executing code, (3) employing error-based reflection for improved robustness, and (4) allowing iterative refinement through multi-round conversations. We construct two datasets from academic coursework materials and published research papers to evaluate performance against real-world challenges. Comparative testing shows our domain-specialized agent significantly outperforms both benchmark large language models (LLMs) and general-purpose AI agents. This work establishes a testbed for exploring AI's impact on social science research and enables cost-effective integration of domain expertise, making advanced econometric methods accessible to users with minimal coding expertise. Furthermore, our agent enhances research reproducibility and offers promising pedagogical applications for econometrics teaching.
Previous research has sought to enhance the graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data. While these led to specialized LLMs better at solving graph algorithm problems, we don't need LLMs for shortest path: we need generalization from synthetic graph data to real-world tasks with implicit graph structures. In this work, we propose to unlock generalizable learning of graph synthetic data with reinforcement learning. We first design solution-based and process-based rewards for synthetic graph problems: instead of rigid memorizing response patterns in direct fine-tuning, we posit that RL would help LLMs grasp the essentials underlying graph reasoning and alleviate overfitting. We employ RL algorithms such as GRPO and DPO, aligning both off-the-shelf LLMs and LLMs fine-tuned on synthetic graph data. We then compare them against existing settings on both in-domain synthetic tasks and out-of-domain real-world tasks with implicit graph structures such as multi-hop QA, structured planning, and more. Extensive experiments demonstrate that our RL recipe leads to statistically significant improvement on 5 datasets, with an average gain of 12.9\% over baseline settings. Further analysis reveals that process-based rewards consistently outperform solution-based rewards, mixing synthetic and real-world task data yields potential gains, while compositionality and explainable intermediate steps remains a critical challenge even after RL.
Knowledge editing aims to efficiently update Large Language Models (LLMs) by modifying specific knowledge without retraining the entire model. Among knowledge editing approaches, in-context editing (ICE) offers a lightweight solution by injecting new knowledge directly into the input context, leaving model parameters unchanged. However, existing ICE approaches do not explicitly separate the newly injected knowledge from the model's original reasoning process. This entanglement often results in conflicts between external updates and internal parametric knowledge, undermining the consistency and accuracy of the reasoning path.In this work, we conduct preliminary experiments to examine how parametric knowledge influences reasoning path planning. We find that the model's reasoning is tightly coupled with its internal knowledge, and that naively injecting new information without adapting the reasoning path often leads to performance degradation, particularly in multi-hop tasks. To this end, we propose DecKER, a novel ICE framework that decouples reasoning from knowledge editing by generating a masked reasoning path and then resolving knowledge edits via hybrid retrieval and model-based validation. Experiments on multi-hop QA benchmarks show that DecKER significantly outperforms existing ICE methods by mitigating knowledge conflicts and preserving reasoning consistency. Our code is available at: https://github.com/bebr2/DecKER .
Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address this, we first introduce the 3E Criteria to systematically assess the cost-effectiveness of search strategies, revealing that existing methods often trade significant efficiency for marginal performance gains. To improve LLM decision-making while maintaining efficiency, we propose the Speculative Reward Model (SRM), a plug-and-play framework that seamlessly integrates with existing search strategies. Specifically, SRM employs an external reward assigner to predict optimal actions, reducing reliance on LLMs' internal self-evaluation. And a speculative verification mechanism is used to prune suboptimal choices and guide the search toward more promising steps. We evaluate SRM on several complex decision-making tasks including mathematical reasoning, planning and numerical reasoning in specialized domains. Experimental results show that SRM reduces costs to 1/10 of the original search framework on average while maintaining effectiveness.
Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting complex cognitive behaviors such as verification, goal decomposition, and self-reflection. However, it is unclear what behavior is effective and what behavior is missing for long-horizon AI agents tasks. In this work, we propose Dyna-Think, a thinking framework that integrates planning with an internal world model with reasoning and acting to enhance AI agent performance. To enable Dyna-Think, we propose Dyna-Think Imitation Learning (DIT) and Dyna-Think Dyna Training (DDT). To initialize a policy with Dyna-Think, DIT reconstructs the thinking process of R1 to focus on performing world model simulation relevant to the proposed (and planned) action, and trains the policy using this reconstructed data. To enhance Dyna-Think, DDT uses a two-stage training process to first improve the agent's world modeling ability via objectives such as state prediction or critique generation, and then improve the agent's action via policy training. We evaluate our methods on OSWorld, and demonstrate that Dyna-Think improves the agent's in-domain and out-of-domain performance, achieving similar best-of-n performance compared to R1 while generating 2x less tokens on average. Our extensive empirical studies reveal that 1) using critique generation for world model training is effective to improve policy performance; and 2) AI agents with better performance correlate with better world modeling abilities. We believe our results suggest a promising research direction to integrate world model simulation into AI agents to enhance their reasoning, planning, and acting capabilities.
As language models evolve to tackle complex, multifaceted tasks, their evaluation must adapt to capture this intricacy. A granular, skill-specific understanding of model capabilities can empower researchers to make informed model development plans. In this paper, we introduce SkillVerse, an unsupervised tree-structured diagnosis framework for understanding model proficiency in specific abilities. With LLM as a judge, SkillVerse first critiques the model responses, and then organizes them into a hierarchical structure termed dendrogram. Given proficiency at arbitrary levels of granularity, SkillVerse is flexible to produce insights of behaviors of modern large models. We also demonstrate its efficacy in two downstream tasks: 1) improving model in-context learning by 25% using a tree-search algorithm to select more informative few-shot demonstrations, and 2) accurately predicting new model weaknesses with a 55% success rate, 22% higher than without SkillVerse.
Recent advancements in Large Language Models (LLMs) have demonstrated their potential in planning and reasoning tasks, offering a flexible alternative to classical pathfinding algorithms. However, most existing studies focus on LLMs' independent reasoning capabilities and overlook the potential synergy between LLMs and traditional algorithms. To fill this gap, we propose a comprehensive evaluation benchmark GridRoute to assess how LLMs can take advantage of traditional algorithms. We also propose a novel hybrid prompting technique called Algorithm of Thought (AoT), which introduces traditional algorithms' guidance into prompting. Our benchmark evaluates six LLMs ranging from 7B to 72B parameters across various map sizes, assessing their performance in correctness, optimality, and efficiency in grid environments with varying sizes. Our results show that AoT significantly boosts performance across all model sizes, particularly in larger or more complex environments, suggesting a promising approach to addressing path planning challenges. Our code is open-sourced at https://github.com/LinChance/GridRoute.
Understanding how data moves, transforms, and persists, known as data flow, is fundamental to reasoning in procedural tasks. Despite their fluency in natural and programming languages, large language models (LLMs), although increasingly being applied to decisions with procedural tasks, have not been systematically evaluated for their ability to perform data-flow reasoning. We introduce FABLE, an extensible benchmark designed to assess LLMs' understanding of data flow using structured, procedural text. FABLE adapts eight classical data-flow analyses from software engineering: reaching definitions, very busy expressions, available expressions, live variable analysis, interval analysis, type-state analysis, taint analysis, and concurrency analysis. These analyses are instantiated across three real-world domains: cooking recipes, travel routes, and automated plans. The benchmark includes 2,400 question-answer pairs, with 100 examples for each domain-analysis combination. We evaluate three types of LLMs: a reasoning-focused model (DeepSeek-R1 8B), a general-purpose model (LLaMA 3.1 8B), and a code-specific model (Granite Code 8B). Each model is tested using majority voting over five sampled completions per prompt. Results show that the reasoning model achieves higher accuracy, but at the cost of over 20 times slower inference compared to the other models. In contrast, the general-purpose and code-specific models perform close to random chance. FABLE provides the first diagnostic benchmark to systematically evaluate data-flow reasoning and offers insights for developing models with stronger procedural understanding.
Developing autonomous agents capable of mastering complex, multi-step tasks in unpredictable, interactive environments presents a significant challenge. While Large Language Models (LLMs) offer promise for planning, existing approaches often rely on problematic internal knowledge or make unrealistic environmental assumptions. Although recent work explores learning planning knowledge, they still retain limitations due to partial reliance on external knowledge or impractical setups. Indeed, prior research has largely overlooked developing agents capable of acquiring planning knowledge from scratch, directly in realistic settings. While realizing this capability is necessary, it presents significant challenges, primarily achieving robustness given the substantial risk of incorporating LLMs' inaccurate knowledge. Moreover, efficiency is crucial for practicality as learning can demand prohibitive exploration. In response, we introduce Robust and Efficient Planning for Open-world Agents (REPOA), a novel framework designed to tackle these issues. REPOA features three key components: adaptive dependency learning and fine-grained failure-aware operation memory to enhance robustness to knowledge inaccuracies, and difficulty-based exploration to improve learning efficiency. Our evaluation in two established open-world testbeds demonstrates REPOA's robust and efficient planning, showcasing its capability to successfully obtain challenging late-game items that were beyond the reach of prior approaches.
Recent progress in large language models (LLMs) has enabled tool-augmented agents capable of solving complex real-world tasks through step-by-step reasoning. However, existing evaluations often focus on general-purpose or multimodal scenarios, leaving a gap in domain-specific benchmarks that assess tool-use capabilities in complex remote sensing use cases. We present ThinkGeo, an agentic benchmark designed to evaluate LLM-driven agents on remote sensing tasks via structured tool use and multi-step planning. Inspired by tool-interaction paradigms, ThinkGeo includes human-curated queries spanning a wide range of real-world applications such as urban planning, disaster assessment and change analysis, environmental monitoring, transportation analysis, aviation monitoring, recreational infrastructure, and industrial site analysis. Each query is grounded in satellite or aerial imagery and requires agents to reason through a diverse toolset. We implement a ReAct-style interaction loop and evaluate both open and closed-source LLMs (e.g., GPT-4o, Qwen2.5) on 436 structured agentic tasks. The benchmark reports both step-wise execution metrics and final answer correctness. Our analysis reveals notable disparities in tool accuracy and planning consistency across models. ThinkGeo provides the first extensive testbed for evaluating how tool-enabled LLMs handle spatial reasoning in remote sensing. Our code and dataset are publicly available
Large Language Model (LLM)-based multi-agent systems show promise for automating real-world tasks but struggle to transfer across domains due to their domain-specific nature. Current approaches face two critical shortcomings: they require complete architectural redesign and full retraining of all components when applied to new domains. We introduce Workforce, a hierarchical multi-agent framework that decouples strategic planning from specialized execution through a modular architecture comprising: (i) a domain-agnostic Planner for task decomposition, (ii) a Coordinator for subtask management, and (iii) specialized Workers with domain-specific tool-calling capabilities. This decoupling enables cross-domain transferability during both inference and training phases: During inference, Workforce seamlessly adapts to new domains by adding or modifying worker agents; For training, we introduce Optimized Workforce Learning (OWL), which improves generalization across domains by optimizing a domain-agnostic planner with reinforcement learning from real-world feedback. To validate our approach, we evaluate Workforce on the GAIA benchmark, covering various realistic, multi-domain agentic tasks. Experimental results demonstrate Workforce achieves open-source state-of-the-art performance (69.70%), outperforming commercial systems like OpenAI's Deep Research by 2.34%. More notably, our OWL-trained 32B model achieves 52.73% accuracy (+16.37%) and demonstrates performance comparable to GPT-4o on challenging tasks. To summarize, by enabling scalable generalization and modular domain transfer, our work establishes a foundation for the next generation of general-purpose AI assistants.
Small Uncrewed Aerial Systems (sUAS) are increasingly deployed as autonomous swarms in search-and-rescue and other disaster-response scenarios. In these settings, they use computer vision (CV) to detect objects of interest and autonomously adapt their missions. However, traditional CV systems often struggle to recognize unfamiliar objects in open-world environments or to infer their relevance for mission planning. To address this, we incorporate large language models (LLMs) to reason about detected objects and their implications. While LLMs can offer valuable insights, they are also prone to hallucinations and may produce incorrect, misleading, or unsafe recommendations. To ensure safe and sensible decision-making under uncertainty, high-level decisions must be governed by cognitive guardrails. This article presents the design, simulation, and real-world integration of these guardrails for sUAS swarms in search-and-rescue missions.
Embodied visual tracking is a fundamental skill in Embodied AI, enabling an agent to follow a specific target in dynamic environments using only egocentric vision. This task is inherently challenging as it requires both accurate target recognition and effective trajectory planning under conditions of severe occlusion and high scene dynamics. Existing approaches typically address this challenge through a modular separation of recognition and planning. In this work, we propose TrackVLA, a Vision-Language-Action (VLA) model that learns the synergy between object recognition and trajectory planning. Leveraging a shared LLM backbone, we employ a language modeling head for recognition and an anchor-based diffusion model for trajectory planning. To train TrackVLA, we construct an Embodied Visual Tracking Benchmark (EVT-Bench) and collect diverse difficulty levels of recognition samples, resulting in a dataset of 1.7 million samples. Through extensive experiments in both synthetic and real-world environments, TrackVLA demonstrates SOTA performance and strong generalizability. It significantly outperforms existing methods on public benchmarks in a zero-shot manner while remaining robust to high dynamics and occlusion in real-world scenarios at 10 FPS inference speed. Our project page is: https://pku-epic.github.io/TrackVLA-web.