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
119 results for “keyword:"llm reasoning"” in ICLR 2027. 23 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment▼4.3k2.00
[PDF]CARVE: Coordinating Imitation and Exploration through Reward Variance for LLM Reasoning Post-Training▼1361.33
[PDF]CoRD: Conjecture-and-Refutation Decoding for Evidence-Gated Overrides in Collaborative Reasoning▼5.8k2.33
[PDF]Where Should the Credit Lie? Attention-Induced Anchor-Bridge Attribution Policy Optimization for LLM Reasoning▼4.3k2.00
[PDF]Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation▼1.2k1.67
[PDF]An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning▼5.8k2.33
[PDF]DelTA: Discriminative Token Credit Assignment for Reinforcement Learning with Verifiable Rewards▲5103.00
[PDF]Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities▲3952.67
[PDF]TRUSTCONS: EXACTLY VERIFYING CONSISTENCY, COMPLETENESS , AND CONDITIONED RE-ENUMERATION IN LANGUAGE MODELS▼1361.33
[PDF]Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction▲3952.67
[PDF]Gradient Descent on Tokens Is Sparse: Understanding the Computational Structure of Differentiable Token Optimization▼4.3k2.00
[PDF]Cool the Sampler, Not the Learner: Sampling Temperature Moves the Staleness Cliff of Importance-Corrected GRPO▼4.3k2.00
Withdrawn or desk rejected (23)
[PDF]Adapt Only When It Pays: Selective, Verifiable Test-Time Self-Training for LLM ReasoningWithdrawn1.00
[PDF]When Revision Backfires: Consequence-Aware Verification for Multi-Role LLM ReasoningDesk rejected2.67
[PDF]Principled Reinforcement Learning with Verifiable Rewards: Understanding LLM Reasoning via Diffusive FlowWithdrawn1.33