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145 results for “keyword:"reasoning models"” in ICLR 2027. 20 withdrawn or desk rejected listed apart.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]Compile2Decide: Distilling Frontier Reasoning Models into Fast Calibrated Decision Models▼4.3k2.00
[PDF]Committed by the First Token: Measuring Recovery from Induced Answer Commitment in Chain-of-Thought Reasoning▼4.3k2.00
[PDF]Mimir: A Sub-2B Hierarchical Reasoning Model Trained on Permissible Data Punches Above Its Weight Class▼1.2k1.67
[PDF]Decoupling Capabilities via Sample-Level Geometric Routing for Parameter-Efficient Low-Resource Adaptation▲6.1k2.00
[PDF]THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models▼1.2k1.67
[PDF]How Far Can Reasoning Alone Take You? Graph-Based Candidate Selection for Test-Time Scaling on Code▲3952.67
[PDF]RazorReward-RL: Capability-Aware Efficiency Optimization for LLM Reasoning via Razor Reward▲9.2k2.67
[PDF]ROAST: Reducing Overthinking in Reasoning via Advantage Reshaping and State-aware Termination▼4.3k2.00
[PDF]Reflect Less, Reason Better: Entropy-Aware Reflection Rewards for Efficient Large Reasoning Models▲14k3.00
[PDF]TERSE: Trace-Efficiency Reward via Squeezing rEdundancy for Efficient Large Reasoning Models▲5.7k2.00
Withdrawn or desk rejected (20)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