{"total":14,"rows":[{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2601.05503","title":"Over-Searching in Search-Augmented Large Language Models","created":"2026-01-09","cited_by_count":11,"area":null},{"id":"2602.04755","title":"When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2601.21257","title":"MoCo: A One-Stop Shop for Model Collaboration Research","created":"2026-01-29","cited_by_count":6,"area":null},{"id":"2507.23407","title":"Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration","created":"2025-07-31","cited_by_count":5,"area":null},{"id":"2604.22779","title":"KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2602.01875","title":"PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2606.20585","title":"Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.17621","title":"Mechanistic Attention Guidance for Agent Memory Refinement","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2610.02444","title":"Counterexample Generation via Per-Theorem Symbolic Verifiers: When Imitation Hurts and Reinforcement Repairs","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.03190","title":"Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.08413","title":"Knowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification Signals","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}