{"total":21,"rows":[{"id":"2608.09867","title":"Stealing Reasoning Traces from Proprietary LLM APIs","created":"2026-08-10","cited_by_count":9,"area":"lr"},{"id":"2609.04565","title":"Extremely Sparse Supervision Incentivizes Reasoning Ability","created":"2026-09-03","cited_by_count":5,"area":"lr"},{"id":"2609.18708","title":"Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening","created":"2026-09-16","cited_by_count":2,"area":"lr"},{"id":"2609.11319","title":"Magenta: Closing the Loop Between Mathematical Reasoning and Lean Verification","created":"2026-09-10","cited_by_count":1,"area":"lr"},{"id":"2609.00264","title":"The Answer Is Not the Argument","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.06970","title":"CantoneseLLM v2: Reasoning in a Low-Resource Language","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.07036","title":"Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.12606","title":"Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geometry Problem Solving","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.25442","title":"WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.32913","title":"Allspark: Weak to Strong Transfer via Alternating Chain of Thought","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.34344","title":"Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34492","title":"PowerBench: A Benchmark for Agentic Retrieval and Reasoning in Power Systems","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34863","title":"Revisit to Segment: Working Memory Distillation for Reasoning Segmentation","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.39118","title":"Diagnosing On-Policy Self-Distillation for Reasoning Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39371","title":"EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39801","title":"RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.04596","title":"DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.10889","title":"SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.11918","title":"From Surface to Depth: Towards Cognitive Appraisal Reasoning in Multimodal Emotion Understanding","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.12061","title":"When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.18861","title":"Hybrid Reasoning Agents","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}