{"total":16,"rows":[{"id":"2504.07934","title":"SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement","created":"2025-04-10","cited_by_count":145,"area":"lr"},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50,"area":"lr"},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","cited_by_count":43,"area":"lr"},{"id":"2505.00661","title":"On the generalization of language models from in-context learning and finetuning: a controlled study","created":"2025-05-01","cited_by_count":40,"area":"lr"},{"id":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","created":"2025-09-03","cited_by_count":20,"area":"lr"},{"id":"2505.21479","title":"Are Language Models Consequentialist or Deontological Moral Reasoners?","created":"2025-05-27","cited_by_count":12,"area":"lr"},{"id":"2510.06108","title":"Influence Functions for Efficient Data Selection in Reasoning","created":"2025-10-07","cited_by_count":10,"area":"lr"},{"id":"2505.22308","title":"Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning","created":"2025-05-28","cited_by_count":9,"area":"lr"},{"id":"2505.19949","title":"Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2509.00072","title":"Test of Time: Rethinking Temporal Signal of Benchmark Contamination","created":"2025-08-26","cited_by_count":3,"area":"lr"},{"id":"2512.13279","title":"AIR: Post-training Data Selection for Reasoning via Attention Head Influence","created":"2025-12-15","cited_by_count":3,"area":"lr"},{"id":"2502.20620","title":"Rectifying Belief Space via Unlearning to Harness LLMs' Reasoning","created":"2025-02-28","cited_by_count":2,"area":"lr"},{"id":"2511.13726","title":"Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2602.22583","title":"Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2602.03640","title":"Tutorial on Reasoning for IR & IR for Reasoning","created":"2026-02-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}