{"total":20,"rows":[{"id":"2509.22638","title":"Language Models Can Learn from Verbal Feedback Without Scalar Rewards","created":"2025-09-26","cited_by_count":18,"area":null},{"id":"2510.24697","title":"WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking","created":"2025-10-28","cited_by_count":18,"area":null},{"id":"2602.17616","title":"Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs","created":"2026-02-19","cited_by_count":11,"area":null},{"id":"2602.07078","title":"The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL","created":"2026-02-06","cited_by_count":6,"area":null},{"id":"2604.19749","title":"The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?","created":"2026-03-03","cited_by_count":6,"area":null},{"id":"2602.12351","title":"LongNav-R1: Horizon-Adaptive Multi-Turn RL for Long-Horizon VLA Navigation","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2512.01224","title":"CoSineVerifier: Tool-Augmented Answer Verification for Computation-Oriented Scientific Questions","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2509.24923","title":"When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2601.21654","title":"ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2602.15898","title":"MultiCube-RAG for Multi-hop Question Answering","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2603.19470","title":"Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2605.08666","title":"The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2512.23087","title":"Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2605.28751","title":"Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2605.04719","title":"Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2607.18256","title":"PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2608.01743","title":"Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.08557","title":"OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2609.18135","title":"DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.25678","title":"Toolcompass: Guiding Tool Trialing, Not Suppressing It","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}