{"list":"other","total":102,"rows":[{"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":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"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":"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":"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":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634},{"id":"2402.02716","title":"Understanding the planning of LLM agents: A survey","created":"2024-02-05","cited_by_count":421},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2503.09572","title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","created":"2025-03-12","cited_by_count":195},{"id":"2504.00906","title":"Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents","created":"2025-04-01","cited_by_count":159},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156},{"id":"2510.11967","title":"Scaling Long-Horizon LLM Agent via Context-Folding","created":"2025-10-13","cited_by_count":148},{"id":"2506.14866","title":"OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents","created":"2025-06-17","cited_by_count":111},{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102},{"id":"2410.06992","title":"SWE-Bench+: Enhanced Coding Benchmark for LLMs","created":"2024-10-09","cited_by_count":99},{"id":"2502.15840","title":"Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents","created":"2025-02-20","cited_by_count":80},{"id":"2511.08325","title":"AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress","created":"2025-11-11","cited_by_count":77},{"id":"2505.23564","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","created":"2025-05-29","cited_by_count":75},{"id":"2508.04700","title":"SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience","created":"2025-08-06","cited_by_count":69},{"id":"2504.13865","title":"A Survey on (M)LLM-Based GUI Agents","created":"2025-03-27","cited_by_count":62},{"id":"2508.19005","title":"Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark","created":"2025-08-26","cited_by_count":45},{"id":"2405.14092","title":"Large Language Models Can Self-Correct with Key Condition Verification","created":"2024-05-23","cited_by_count":39},{"id":"2412.11006","title":"Entropy-Regularized Process Reward Model","created":"2024-12-15","cited_by_count":38},{"id":"2503.18971","title":"LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models","created":"2025-03-22","cited_by_count":38},{"id":"2607.07663","title":"Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops","created":"2026-07-08","cited_by_count":35},{"id":"2408.14354","title":"SWE-bench-java: A GitHub Issue Resolving Benchmark for Java","created":"2024-08-26","cited_by_count":34},{"id":"2402.08702","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","created":"2024-02-13","cited_by_count":32},{"id":"2506.04135","title":"macOSWorld: A Multilingual Interactive Benchmark for GUI Agents","created":"2025-06-04","cited_by_count":32},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31},{"id":"2510.20022","title":"SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph","created":"2025-10-22","cited_by_count":28},{"id":"2602.05665","title":"Graph-based Agent Memory: Taxonomy, Techniques, and Applications","created":"2026-02-05","cited_by_count":25},{"id":"2601.04035","title":"MobileDreamer: Generative Sketch World Model for GUI Agent","created":"2026-01-07","cited_by_count":23},{"id":"2506.01080","title":"The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process","created":"2025-06-01","cited_by_count":21},{"id":"2505.16265","title":"Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models","created":"2025-05-22","cited_by_count":16},{"id":"2511.12997","title":"WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance","created":"2025-11-17","cited_by_count":16},{"id":"2512.10218","title":"Does SWE-Bench-Verified Test Agent Ability or Model Memory?","created":"2025-12-11","cited_by_count":16},{"id":"2505.13271","title":"CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning","created":"2025-05-19","cited_by_count":15},{"id":"2508.00031","title":"Git Context Controller: Manage the Context of LLM-based Agents like Git","created":"2025-07-30","cited_by_count":15},{"id":"2512.09882","title":"Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing","created":"2025-12-10","cited_by_count":15},{"id":"2604.20987","title":"Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks","created":"2026-04-22","cited_by_count":15},{"id":"2412.04272","title":"PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables","created":"2024-12-05","cited_by_count":14},{"id":"2601.18642","title":"FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory","created":"2026-01-26","cited_by_count":14},{"id":"2503.06951","title":"ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA","created":"2025-03-10","cited_by_count":13},{"id":"2508.07935","title":"SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows","created":"2025-08-11","cited_by_count":13},{"id":"2512.09187","title":"WOLF: Werewolf-based Observations for LLM Deception and Falsehoods","created":"2025-12-09","cited_by_count":13},{"id":"2601.20380","title":"OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution","created":"2026-01-28","cited_by_count":13},{"id":"2603.00680","title":"MemPO: Self-Memory Policy Optimization for Long-Horizon Agents","created":"2026-02-28","cited_by_count":12},{"id":"2607.05202","title":"EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer","created":"2026-07-06","cited_by_count":11},{"id":"2509.21154","title":"GRPO is Secretly a Process Reward Model","created":"2025-09-25","cited_by_count":10},{"id":"2510.14942","title":"GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling for Step-Level Reasoning","created":"2025-10-16","cited_by_count":10},{"id":"2604.17849","title":"On the Reliability of Computer Use Agents","created":"2026-04-20","cited_by_count":10},{"id":"2605.21768","title":"Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents","created":"2026-05-20","cited_by_count":10},{"id":"2507.11059","title":"SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks","created":"2025-07-15","cited_by_count":9},{"id":"2601.07577","title":"Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents","created":"2026-01-12","cited_by_count":9},{"id":"2506.12482","title":"Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety","created":"2025-06-14","cited_by_count":8},{"id":"2506.17208","title":"Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems","created":"2025-06-20","cited_by_count":8},{"id":"2601.00828","title":"Decomposing LLM Self-Correction: The Accuracy-Correction Paradox and Error Depth Hypothesis","created":"2025-12-24","cited_by_count":8},{"id":"2603.21972","title":"Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe","created":"2026-03-23","cited_by_count":8},{"id":"2606.22528","title":"Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents","created":"2026-06-21","cited_by_count":8},{"id":"2507.13081","title":"iReDev: A Knowledge-Driven Multi-Agent Framework for Intelligent Requirements Development","created":"2025-07-17","cited_by_count":6},{"id":"2511.15755","title":"Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for Incident Response","created":"2025-11-19","cited_by_count":6},{"id":"2605.08580","title":"Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents","created":"2026-05-09","cited_by_count":6},{"id":"2605.15377","title":"Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute","created":"2026-05-14","cited_by_count":6},{"id":"2510.07091","title":"The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas","created":"2025-10-08","cited_by_count":5},{"id":"2602.02556","title":"Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs","created":"2026-01-30","cited_by_count":5},{"id":"2603.24631","title":"Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code","created":"2026-03-25","cited_by_count":5},{"id":"2605.05965","title":"Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR","created":"2026-05-07","cited_by_count":5},{"id":"2605.18565","title":"MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems","created":"2026-05-18","cited_by_count":5},{"id":"2510.05625","title":"Generative AI-Driven Hierarchical Multi-Agent Framework for Zero-Touch Optical Networks","created":"2025-10-07","cited_by_count":4},{"id":"2605.11225","title":"PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement","created":"2026-05-11","cited_by_count":4},{"id":"2605.29960","title":"Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction","created":"2026-05-28","cited_by_count":4},{"id":"2606.07367","title":"Self-evolving LLM agents with in-distribution Optimization","created":"2026-06-05","cited_by_count":4},{"id":"2606.22953","title":"Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents","created":"2026-06-22","cited_by_count":4},{"id":"2508.13171","title":"Cognitive Workspace: Active Memory Management for LLMs -- An Empirical Study of Functional Infinite Context","created":"2025-08-08","cited_by_count":3},{"id":"2509.13021","title":"xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Models","created":"2025-09-16","cited_by_count":3},{"id":"2509.24219","title":"ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning","created":"2025-09-29","cited_by_count":3},{"id":"2603.06194","title":"MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue","created":"2026-03-06","cited_by_count":3},{"id":"2604.04782","title":"Cheap Talk, Empty Promise: Frontier LLMs easily break public promises for self-interest","created":"2026-04-06","cited_by_count":3},{"id":"2605.07313","title":"When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory","created":"2026-05-08","cited_by_count":3},{"id":"2606.07889","title":"Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories","created":"2026-06-05","cited_by_count":3},{"id":"2606.29718","title":"Diagnosing and Mitigating Context Rot in Long-horizon Search","created":"2026-06-29","cited_by_count":3},{"id":"2412.14212","title":"Tree-of-Code: A Hybrid Approach for Robust Complex Task Planning and Execution","created":"2024-12-18","cited_by_count":2},{"id":"2506.07557","title":"SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition","created":"2025-06-09","cited_by_count":2},{"id":"2506.15894","title":"Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning","created":"2025-06-18","cited_by_count":2},{"id":"2512.06983","title":"On Memory: A comparison of memory mechanisms in world models","created":"2025-12-07","cited_by_count":2},{"id":"2602.04449","title":"What's in a Benchmark? The Case of SWE-Bench in Automated Program Repair","created":"2026-02-04","cited_by_count":2},{"id":"2605.13850","title":"A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution Topology","created":"2026-03-16","cited_by_count":2},{"id":"2605.21516","title":"Harnesses for Inference-Time Alignment over Execution Trajectories","created":"2026-05-15","cited_by_count":2},{"id":"2606.30566","title":"Forensic Trajectory Signatures for Agent Memory Poisoning Detection","created":"2026-06-29","cited_by_count":2},{"id":"2607.10750","title":"Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF","created":"2026-07-12","cited_by_count":2},{"id":"2508.18108","title":"SentiMM: A Multimodal Multi-Agent Framework for Sentiment Analysis in Social Media","created":"2025-08-25","cited_by_count":1},{"id":"2510.17431","title":"Agentic Reinforcement Learning for Search Misaligns Instruction-Tuning","created":"2025-10-20","cited_by_count":1}],"next_cursor":"100"}