{"total":36,"rows":[{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208,"area":"lr"},{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138,"area":"lr"},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2508.02085","title":"SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents","created":"2025-08-04","cited_by_count":69,"area":"lr"},{"id":"2510.08191","title":"Training-Free Group Relative Policy Optimization","created":"2025-10-09","cited_by_count":55,"area":"lr"},{"id":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2502.14565","title":"ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification","created":"2025-02-20","cited_by_count":35,"area":"lr"},{"id":"2409.09584","title":"RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation","created":"2024-09-15","cited_by_count":26,"area":"lr"},{"id":"2503.23803","title":"Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute","created":"2025-03-31","cited_by_count":26,"area":"lr"},{"id":"2505.19435","title":"Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection","created":"2025-05-26","cited_by_count":23,"area":"lr"},{"id":"2601.22311","title":"Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents","created":"2026-01-29","cited_by_count":23,"area":"lr"},{"id":"2508.01432","title":"TripTailor: A Real-World Benchmark for Personalized Travel Planning","created":"2025-08-02","cited_by_count":22,"area":"lr"},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2506.00750","title":"CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning","created":"2025-05-31","cited_by_count":13,"area":"lr"},{"id":"2511.00330","title":"Sherlock: Reliable and Efficient Agentic Workflow Execution","created":"2025-11-01","cited_by_count":11,"area":"lr"},{"id":"2411.05010","title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","created":"2024-10-22","cited_by_count":10,"area":"lr"},{"id":"2604.24432","title":"Kwai Summary Attention Technical Report","created":"2026-04-27","cited_by_count":7,"area":"lr"},{"id":"2505.16832","title":"From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2509.13758","title":"A Study on Thinking Patterns of Large Reasoning Models in Code Generation","created":"2025-09-17","cited_by_count":5,"area":"lr"},{"id":"2605.09907","title":"RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation","created":"2026-05-11","cited_by_count":5,"area":"lr"},{"id":"2607.25996","title":"RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models","created":"2026-07-28","cited_by_count":5,"area":"lr"},{"id":"2410.19245","title":"MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming","created":"2024-10-25","cited_by_count":3,"area":"lr"},{"id":"2604.15075","title":"Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2406.04464","title":"On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editing","created":"2024-06-06","cited_by_count":2,"area":"lr"},{"id":"2505.13008","title":"Adversarial Reasoning for Repair Based on Inferred Program Intent","created":"2025-05-19","cited_by_count":2,"area":"lr"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2501.07054","title":"PoAct: Policy and Action Dual-Control Agent for Generalized Applications","created":"2025-01-13","cited_by_count":1,"area":"lr"},{"id":"2506.17462","title":"General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting","created":"2025-06-20","cited_by_count":1,"area":"lr"},{"id":"2605.07251","title":"Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2603.18334","title":"Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2606.26935","title":"Where Do CoT Training Gains Land in LLM based Agents?","created":"2026-06-25","cited_by_count":0,"area":"lr"},{"id":"2607.27415","title":"Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2610.07835","title":"DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}