{"total":18,"rows":[{"id":"2604.09459","title":"From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models","created":"2026-04-10","cited_by_count":23,"area":"lr"},{"id":"2512.04220","title":"On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement","created":"2025-12-03","cited_by_count":15,"area":"lr"},{"id":"2603.12634","title":"Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents","created":"2026-03-13","cited_by_count":11,"area":"lr"},{"id":"2601.10712","title":"MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching","created":"2026-01-15","cited_by_count":10,"area":"lr"},{"id":"2604.14267","title":"Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization","created":"2026-04-15","cited_by_count":9,"area":"lr"},{"id":"2605.22511","title":"Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning","created":"2026-05-21","cited_by_count":9,"area":"lr"},{"id":"2606.09348","title":"PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment","created":"2026-06-08","cited_by_count":6,"area":"lr"},{"id":"2601.22776","title":"TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2608.12764","title":"Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents","created":"2026-08-13","cited_by_count":2,"area":"lr"},{"id":"2604.08690","title":"Skip-Connected Policy Optimization for Implicit Advantage","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.18235","title":"Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.28354","title":"Plan Before Search: Search Agents Need Plan","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2605.09544","title":"TIDE-Bench: Task-Aware and Diagnostic Evaluation of Tool-Integrated Reasoning","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.13534","title":"Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2605.26037","title":"Peak-Then-Collapse and the Four Interface Channels of Knowledge-Graph Tool Use","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2607.18915","title":"Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM","created":"2026-07-21","cited_by_count":0,"area":"lr"},{"id":"2607.27652","title":"Harness-G: A Graph-Structured Harness for Search Agents","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2609.36178","title":"Targeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}