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145 results for “keyword:"reasoning models"” in ICLR 2027. 20 withdrawn or desk rejected listed apart.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]FlowWeaver: Weaving Reasoning Paths with Cross-Trajectory Flow for Fine-Grained Credit Assignment▲4002.67
[PDF]Constructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning Models▼1.2k1.67
[PDF]Probing the Emergent Global Workspace of Reasoning Models on Structured Reasoning Tasks▲9.2k2.67
[PDF]KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization▲5103.00
[PDF]Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization▼1.2k1.67
[PDF]When to Use the Solution: Preserving Exploration in On-Policy Self-Distillation for Reasoning Models▼4.3k2.00
[PDF]On the Interplay between Backtracking and Latent Confidence Directions in Reasoning Models▼1.2k3.00
[PDF]How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum▲4002.67
[PDF]Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning▼1.1k3.25
Withdrawn or desk rejected (20)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