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119 results for “keyword:"llm reasoning"” in ICLR 2027. 23 withdrawn or desk rejected listed apart.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]Relative Capability Organizes the Geometry of Answer Distributions in Test-Time Scaling▼4.5k2.67
[PDF]Communication as Evidence Routing: Adaptive Relational Graphs via Optimal Transport for Multi-Agent LLM Reasoning▲13k2.33
[PDF]Which Updates Erase What the Base Model Knew? Optimizer-Conditioned Attribution of Reasoning-Support Loss in RLVR▼5.8k2.33
[PDF]When Do RTL Verifiers Lie? Measuring Proxy-Reward Overoptimization in LLM Hardware Design▼4.5k2.67
[PDF]Memorized or Memo-rized: Prior Leakage of Procedural Knowledge in Large Language Models▲3.0k2.33
[PDF]Half the Rollouts, No Measurable Cost: A Seeded Audit of Dynamic Sampling and Credit Assignment in DAPO▼1.2k1.67
[PDF]ChronoCheck: Scale Improves Per-Claim Faithfulness but Shifts Time-Series Rationales Toward the Claims Models Get Wrong▼1.2k1.67
[PDF]I Know That I Know Nothing: Narrowing the Knowledge-Output Gap in Large Language Models through Early High-Entropy Token Intervention▲3.0k2.33
[PDF]When Should Self-Consistency Trust Trajectory Signals? Competition-Aware Reselection for LLM Reasoning▼1.2k1.67
[PDF]StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling▲14k3.00
[PDF]Complementary Evidence Reasoning over Structured and Unstructured Electronic Health Records▼5.8k2.33
Withdrawn or desk rejected (23)
[PDF]DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold AlignmentWithdrawn1.00