{"total":16,"rows":[{"id":"2410.08633","title":"Transformers Provably Solve Parity Efficiently with Chain of Thought","created":"2024-10-11","cited_by_count":50,"area":"lr"},{"id":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2410.03663","title":"Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review","created":"2024-10-04","cited_by_count":14,"area":"lr"},{"id":"2508.16695","title":"Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?","created":"2025-08-21","cited_by_count":11,"area":"lr"},{"id":"2505.13792","title":"Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2510.12157","title":"Self-Verifying Reflection Helps Transformers with CoT Reasoning","created":"2025-10-14","cited_by_count":4,"area":"lr"},{"id":"2510.02227","title":"More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration","created":"2025-10-02","cited_by_count":3,"area":"lr"},{"id":"2605.08625","title":"Reasoning-Aware Training for Time Series Forecasting","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2603.26778","title":"TED: Training-Free Experience Distillation for Multimodal Reasoning","created":"2026-03-25","cited_by_count":2,"area":"lr"},{"id":"2410.16924","title":"SleepCoT: A Lightweight Personalized Sleep Health Model via Chain-of-Thought Distillation","created":"2024-10-22","cited_by_count":1,"area":"lr"},{"id":"2603.19266","title":"Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2511.01354","title":"Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series","created":"2025-11-03","cited_by_count":0,"area":"lr"},{"id":"2602.22508","title":"Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2608.29662","title":"ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2610.00332","title":"The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.09587","title":"Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation","created":"2026-10-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}