{"total":20,"rows":[{"id":"2607.22724","title":"Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-07-22","cited_by_count":9,"area":"agents"},{"id":"2608.16156","title":"TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents","created":"2026-08-17","cited_by_count":7,"area":"agents"},{"id":"2608.19842","title":"SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2608.06861","title":"Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents","created":"2026-08-07","cited_by_count":2,"area":"agents"},{"id":"2608.18524","title":"DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents","created":"2026-08-19","cited_by_count":2,"area":"agents"},{"id":"2608.19803","title":"MileGPO: Milestone Inference with Local Evidence for Graph-Based Policy Optimization of Long-Horizon LLM Agents","created":"2026-08-20","cited_by_count":2,"area":"agents"},{"id":"2607.16169","title":"When Does Muon Help Agentic Reinforcement Learning?","created":"2026-07-17","cited_by_count":1,"area":"agents"},{"id":"2608.08255","title":"Learning from Environmental Feedback: Credit Assignment across Multiple Timescales for Agentic Reinforcement Learning","created":"2026-08-08","cited_by_count":1,"area":"agents"},{"id":"2609.03383","title":"TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM Agents","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2609.32577","title":"Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL","created":"2026-09-26","cited_by_count":1,"area":"agents"},{"id":"2609.32430","title":"Multi-Agent System Search via Active Substructure-aware Policy Optimization","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.32631","title":"SWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.34810","title":"UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.35058","title":"TIDE: Teacher-Student Transition via Informative Distillation and Exploration for Agentic RL","created":"2026-09-28","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":"2610.01207","title":"Dependency-Aware Reward Shaping for Agentic Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.08402","title":"VETTA: Coordinating Turn- and Token-Level Credit Assignment for Multi-Turn LLM Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.12651","title":"SynAct: Synergistic Active Feedback Learning for LLM Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.13755","title":"Matched-Context Group Policy Optimization for LLM Agent Training","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.20195","title":"What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}