{"total":21,"rows":[{"id":"2605.22263","title":"Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning","created":"2026-05-21","cited_by_count":10,"area":"lr"},{"id":"2512.07478","title":"Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization","created":"2025-12-08","cited_by_count":9,"area":"lr"},{"id":"2601.05543","title":"Closing the Modality Reasoning Gap for Speech Large Language Models","created":"2026-01-09","cited_by_count":9,"area":"lr"},{"id":"2601.07036","title":"Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2604.06156","title":"MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control","created":"2026-04-07","cited_by_count":6,"area":"lr"},{"id":"2512.12756","title":"FysicsWorld: A Unified Full-Modality Benchmark for Any-to-Any Understanding, Generation, and Reasoning","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2602.23802","title":"EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models","created":"2026-02-27","cited_by_count":5,"area":"lr"},{"id":"2604.08905","title":"StaRPO: Stability-Augmented Reinforcement Policy Optimization","created":"2026-04-10","cited_by_count":5,"area":"lr"},{"id":"2603.05530","title":"ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation","created":"2026-03-01","cited_by_count":4,"area":"lr"},{"id":"2602.07848","title":"MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation","created":"2026-02-08","cited_by_count":3,"area":"lr"},{"id":"2605.05826","title":"AGPO: Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2601.05633","title":"GIFT: Games as Informal Training for Generalizable LLMs","created":"2026-01-09","cited_by_count":1,"area":"lr"},{"id":"2602.10224","title":"Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2606.16733","title":"A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2606.19771","title":"Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning","created":"2026-06-18","cited_by_count":1,"area":"lr"},{"id":"2602.10006","title":"Answer First, Reason Later: Aligning Search Relevance via Mode-Balanced Reinforcement Learning","created":"2026-02-10","cited_by_count":0,"area":"lr"},{"id":"2605.28699","title":"TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.17735","title":"Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2606.18988","title":"ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2607.08572","title":"Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2609.25463","title":"Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions","created":"2026-09-21","cited_by_count":0,"area":"lr"}],"next_cursor":null}