{"total":40,"rows":[{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276,"area":"agents"},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191,"area":"agents"},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548,"area":"agents"},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429,"area":"agents"},{"id":"2310.05915","title":"FireAct: Toward Language Agent Fine-tuning","created":"2023-10-09","cited_by_count":256,"area":"agents"},{"id":"2402.11208","title":"Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents","created":"2024-02-17","cited_by_count":137,"area":"agents"},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2512.04388","title":"Learning to Orchestrate Agents in Natural Language with the Conductor","created":"2025-12-04","cited_by_count":23,"area":"agents"},{"id":"2402.15809","title":"Empowering Large Language Model Agents through Action Learning","created":"2024-02-24","cited_by_count":22,"area":"agents"},{"id":"2509.17325","title":"Generalizable End-to-End Tool-Use RL with Synthetic CodeGym","created":"2025-09-22","cited_by_count":17,"area":"agents"},{"id":"2402.06700","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","created":"2024-02-09","cited_by_count":12,"area":"agents"},{"id":"2504.04220","title":"AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation","created":"2025-04-05","cited_by_count":8,"area":"agents"},{"id":"2510.23272","title":"Code Aesthetics with Agentic Reward Feedback","created":"2025-10-27","cited_by_count":6,"area":"agents"},{"id":"2504.20412","title":"kAgent: An execution-guided crash resolution agent for the Linux kernel","created":"2025-04-29","cited_by_count":4,"area":"agents"},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2609.07925","title":"FrogNano: Training a 4B Coding Agent via Online Task Synthesis","created":"2026-09-07","cited_by_count":4,"area":"agents"},{"id":"2405.16854","title":"Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning","created":"2024-05-27","cited_by_count":3,"area":"agents"},{"id":"2503.15129","title":"Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models","created":"2025-03-19","cited_by_count":3,"area":"agents"},{"id":"2508.12555","title":"Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement","created":"2025-08-18","cited_by_count":3,"area":"agents"},{"id":"2601.01569","title":"CaveAgent: Transforming LLMs into Stateful Runtime Operators","created":"2026-01-04","cited_by_count":3,"area":"agents"},{"id":"2604.16335","title":"Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents","created":"2026-03-13","cited_by_count":3,"area":"agents"},{"id":"2605.15301","title":"Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution","created":"2026-05-14","cited_by_count":3,"area":"agents"},{"id":"2404.11964","title":"From Language Models to Practical Self-Improving Computer Agents","created":"2024-04-18","cited_by_count":2,"area":"agents"},{"id":"2609.22068","title":"CodeMidas: Scaling Agentic Coding RL Environments from Code Itself","created":"2026-09-18","cited_by_count":2,"area":"agents"},{"id":"2608.07147","title":"DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2510.22075","title":"Agentic Reinforcement Learning for Real-World Code Repair","created":"2025-10-24","cited_by_count":0,"area":"agents"},{"id":"2603.13019","title":"ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning","created":"2026-03-13","cited_by_count":0,"area":"agents"},{"id":"2604.19856","title":"ChipCraftBrain: Validation-First RTL Generation via Multi-Agent Orchestration","created":"2026-04-21","cited_by_count":0,"area":"agents"},{"id":"2604.23940","title":"Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery","created":"2026-04-27","cited_by_count":0,"area":"agents"},{"id":"2605.08468","title":"PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2605.23382","title":"From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning","created":"2026-05-22","cited_by_count":0,"area":"agents"},{"id":"2607.26307","title":"TraceCoder: Explainable and Auditable Code Generation with Position-Key Snippet Versioning","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2609.12012","title":"Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.31318","title":"AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.35084","title":"GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.03984","title":"Teaching Agents to Code Reliably","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.15708","title":"SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.15964","title":"Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.17710","title":"Adaptive-Group Process Rewards for GUI Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}