{"list":"other","total":91,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"id":"2308.10144","title":"ExpeL: LLM Agents Are Experiential Learners","created":"2023-08-20","cited_by_count":876},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548},{"id":"2403.02691","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","created":"2024-03-05","cited_by_count":538},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468},{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437},{"id":"2407.18901","title":"AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents","created":"2024-07-26","cited_by_count":401},{"id":"2409.07429","title":"Agent Workflow Memory","created":"2024-09-11","cited_by_count":383},{"id":"2403.07718","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","created":"2024-03-12","cited_by_count":363},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"2401.13178","title":"AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents","created":"2024-01-24","cited_by_count":339},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2408.04682","title":"ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities","created":"2024-08-08","cited_by_count":295},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"1301.2300","title":"Direct and Indirect Effects","created":"2013-01-10","cited_by_count":280},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274},{"id":"2305.11554","title":"ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings","created":"2023-05-19","cited_by_count":240},{"id":"2405.17935","title":"Tool Learning with Large Language Models: A Survey","created":"2024-05-28","cited_by_count":223},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219},{"id":"2409.00920","title":"ToolACE: Winning the Points of LLM Function Calling","created":"2024-09-02","cited_by_count":216},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204},{"id":"2312.04511","title":"An LLM Compiler for Parallel Function Calling","created":"2023-12-07","cited_by_count":179},{"id":"2407.15711","title":"AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?","created":"2024-07-22","cited_by_count":158},{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152},{"id":"2403.07714","title":"StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models","created":"2024-03-12","cited_by_count":132},{"id":"2309.17428","title":"CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets","created":"2023-09-29","cited_by_count":129},{"id":"2402.04253","title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","created":"2024-02-06","cited_by_count":124},{"id":"2504.06821","title":"Inducing Programmatic Skills for Agentic Tasks","created":"2025-04-09","cited_by_count":111},{"id":"2305.14318","title":"CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models","created":"2023-05-23","cited_by_count":93},{"id":"2407.05291","title":"WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks","created":"2024-07-07","cited_by_count":90},{"id":"2410.03439","title":"ToolGen: Unified Tool Retrieval and Calling via Generation","created":"2024-10-04","cited_by_count":74},{"id":"2311.05657","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","created":"2023-11-09","cited_by_count":72},{"id":"2408.01875","title":"Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval","created":"2024-08-03","cited_by_count":52},{"id":"2503.01763","title":"Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models","created":"2025-03-03","cited_by_count":47},{"id":"2505.06416","title":"ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents","created":"2025-05-09","cited_by_count":36},{"id":"2409.14826","title":"ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback","created":"2024-09-23","cited_by_count":29},{"id":"2406.17465","title":"Enhancing Tool Retrieval with Iterative Feedback from Large Language Models","created":"2024-06-25","cited_by_count":17},{"id":"2602.03338","title":"Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention","created":"2026-02-03","cited_by_count":15},{"id":"2508.05152","title":"Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models","created":"2025-08-07","cited_by_count":8},{"id":"2608.08239","title":"The Replay Gap: Static Evaluation of Model Switching in LLM Agents Scores the Wrong World","created":"2026-08-08","cited_by_count":8},{"id":"2605.24660","title":"How Many Tools Should an LLM Agent See? A Chance-Corrected Answer","created":"2026-05-23","cited_by_count":7},{"id":"1602.01196","title":"Principal stratification analysis using principal scores","created":"2016-02-03","cited_by_count":6},{"id":"2509.20386","title":"Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments","created":"2025-09-22","cited_by_count":6},{"id":"2606.14476","title":"When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More","created":"2026-06-12","cited_by_count":6},{"id":"2606.15017","title":"Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents","created":"2026-06-12","cited_by_count":6},{"id":"2606.18467","title":"ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift","created":"2026-06-16","cited_by_count":6},{"id":"2606.10388","title":"Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval","created":"2026-06-09","cited_by_count":4},{"id":"2607.27083","title":"Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents","created":"2026-07-29","cited_by_count":4},{"id":"2608.02880","title":"Field-Aware Agent Skill Retrieval","created":"2026-08-03","cited_by_count":4},{"id":"2309.12425","title":"Principal Stratification with Continuous Post-Treatment Variables: Nonparametric Identification and Semiparametric Estimation","created":"2023-09-21","cited_by_count":3},{"id":"2607.25718","title":"Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction","created":"2026-07-28","cited_by_count":3},{"id":"2608.26846","title":"Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay","created":"2026-08-27","cited_by_count":3},{"id":"2608.28241","title":"Beyond Task-Only Matching: Personalized Skill Routing with Counterfactual Evaluation","created":"2026-08-28","cited_by_count":3},{"id":"2609.22819","title":"Counterfactual Tool Ranking under Utility, Cost, and Privilege Constraints","created":"2026-09-19","cited_by_count":3},{"id":"2602.16429","title":"TabAgent: A Framework for Replacing Agentic Generative Components with Tabular-Textual Classifiers","created":"2026-02-18","cited_by_count":2},{"id":"2608.16502","title":"When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval","created":"2026-08-17","cited_by_count":2},{"id":"2608.19303","title":"Outcome Monitors: Recovery Affordances for Silent Tool Failures","created":"2026-08-19","cited_by_count":2},{"id":"2608.21375","title":"SchemaRouter: Field-Aware Tool Routing for Efficient Heterogeneous Agentic RAG","created":"2026-07-03","cited_by_count":2},{"id":"2608.22751","title":"Risk-Aware Reranking for Agentic Tool Retrieval","created":"2026-08-24","cited_by_count":2},{"id":"2608.26195","title":"Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation","created":"2026-08-25","cited_by_count":2},{"id":"2609.09395","title":"The Menu Is an Execution Prior: State-Path Tool Menus for Online Agents","created":"2026-09-08","cited_by_count":2},{"id":"2608.18852","title":"SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents","created":"2026-08-19","cited_by_count":1},{"id":"2609.07785","title":"What Does an LLM-Agent Leaderboard Rank Actually Compare?","created":"2026-09-07","cited_by_count":1},{"id":"2609.21187","title":"When Better Turns Do Not Make Better Agents: Diagnosing the Gap Between Next-Turn Metrics and Workflow Success","created":"2026-09-18","cited_by_count":1}],"next_cursor":null}