{"total":20,"rows":[{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58,"area":"lr"},{"id":"2602.15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","created":"2026-02-13","cited_by_count":43,"area":"lr"},{"id":"2512.04307","title":"Evaluating Long-Context Reasoning in LLM-Based WebAgents","created":"2025-12-03","cited_by_count":15,"area":"lr"},{"id":"2605.09359","title":"Skill-R1: Agent Skill Evolution via Reinforcement Learning","created":"2026-05-10","cited_by_count":15,"area":"lr"},{"id":"2502.13131","title":"Rethinking Diverse Human Preference Learning through Principal Component Analysis","created":"2025-02-18","cited_by_count":10,"area":"lr"},{"id":"2507.20936","title":"Dissecting Persona-Driven Reasoning in Language Models via Activation Patching","created":"2025-07-28","cited_by_count":5,"area":"lr"},{"id":"2510.18526","title":"Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2505.17571","title":"Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation","created":"2025-05-23","cited_by_count":4,"area":"lr"},{"id":"2505.21082","title":"RPM: Reasoning-Level Personalization for Black-Box Large Language Models","created":"2025-05-27","cited_by_count":3,"area":"lr"},{"id":"2603.06595","title":"Rethinking Personalization in Large Language Models at the Token Level","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2605.10805","title":"Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2605.11169","title":"OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2606.16316","title":"RL-Index: Reinforcement Learning for Retrieval Index Reasoning","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2602.21219","title":"Reasoning-Based Personalized Generation for Users with Sparse Data","created":"2026-01-31","cited_by_count":1,"area":"lr"},{"id":"2603.10009","title":"Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2604.04300","title":"High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making","created":"2026-04-05","cited_by_count":1,"area":"lr"},{"id":"2604.18041","title":"JudgeMeNot: Personalizing Large Language Models to Emulate Judicial Reasoning in Hebrew","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2603.20170","title":"Learning Dynamic Belief Graphs for Theory-of-mind Reasoning","created":"2026-03-20","cited_by_count":0,"area":"lr"},{"id":"2604.24996","title":"Sparse Personalized Text Generation with Multi-Trajectory Reasoning","created":"2026-04-27","cited_by_count":0,"area":"lr"},{"id":"2610.04132","title":"PB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}