NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
145 results for “keyword:"reasoning models"” in ICLR 2027. 20 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DACPO: Drift-Adaptive Constrained Policy Optimization for Cue-Free Safety Recovery in Large Reasoning Models▲3952.67
[PDF]Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning▲5103.00
[PDF]REIN: Bridging the Gap Between Reasoning and Reliability via Reflection and Abstention Alignment▲3952.67
[PDF]MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller▲9.2k2.67
[PDF]In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners▲2843.00
[PDF]Same Score, Different State: Post-Training Moves Pre-Answer Recoverability under KV Compression▼4.3k2.00
[PDF]When Evaluation Changes the Conclusion: Measuring the Reliability of Small RL Gains in Reasoning LLMs▼4.3k2.00
[PDF]Reasoning Models, Non-Reasoning Answers: Uncovering Reasoning-Bypass Shortcut in MLRMs▼4.3k2.00
[PDF]Hindsight Compacts but Does Not Repair: Rethinking On-Policy Self-Distillation in Reasoning Models▼1.3k1.75
[PDF]Safety Is Discernment, Not Refusal: Teaching Large Reasoning Models to Judge Before They Act▲3952.67
[PDF]Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR▼5.8k2.33
[PDF]RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning▼1.2k1.67
Withdrawn or desk rejected (20)
[PDF]Guided Reasoning Across ISA Dialects: Inference-Time Control for GPU Assembly TranslationWithdrawn1.67
[PDF]Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of ReadoutWithdrawn
[PDF]A benchmark score is not a model property: failure composition changes across operating regimesDesk rejected
[PDF]Not All Recurrence Is Created Equal: Depth Sensitivity Differs Between Recurrence Dimensions of a Single CheckpointWithdrawn1.33