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
2,521 results for “keyword:"reasoning"” in ICLR 2027. 644 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Images Read the Instruction: Bidirectional Attention in Vision-Language-Action Models▲3.0k2.33
[PDF]3D-VL-Fly: A Multi-task 3D Vision–Language Benchmark for Aerial Post-Disaster Damage Assessment▼4.5k2.67
[PDF]Learning to Teach, Learning to Play: Dual Reinforcement Learning with Active Trajectory Inquiry▼4.3k2.00
[PDF]FlowPlan: Flow-Matching Trajectory Planning Guided by Counterfactual Interaction Consequences▼5.8k2.33
[PDF]Bridges over Heavy Hitters: A Causal-HITS Theory and Counterfactual Benchmark for Attention-Graph KV-Cache Compression▲422.75
[PDF]Counterfactual Error Scrambling: Measuring Error-Message Use in Tool-Using Language Agents▼4.3k2.00
[PDF]HAIR: Fine-Strand Hidden-State Anchored Implicit Reasoning with Single-Prefill Inference▲3.0k2.40
[PDF]Coordinate-Dependent Generalization in Transformers: Controlled Interventions and Prospective Prediction on Modular Arithmetic▼1.2k1.67
[PDF]BEAR-Med: From a Clinically Grounded Benchmark to Expert-Aligned Reasoning in Medical Image Forensics▲5.4k3.00
[PDF]FlowWeaver: Weaving Reasoning Paths with Cross-Trajectory Flow for Fine-Grained Credit Assignment▲3942.67
[PDF]One Token Flips the Verdict: Hypergraph Propagation and State Readout Dissociate in Selective Belief Revision▼5.9k2.50
[PDF]Constructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning Models▼1.2k1.67
[PDF]Many Caches, Same Reasoning: Rethinking Importance Selection for Reasoning-Time KV Compression▼1.2k1.67
[PDF]Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning▼4.5k2.67
[PDF]Predicting Reasoning Errors Before They Occur: A Prompt-Side Activation Direction Anticipates Correctness in a Large Language Model▼1361.33
[PDF]Learning When Evidence-Sensitive Guidance Helps: Calibrating Counterfactual On-Policy Distillation for Memory-Grounded Question Answering▼4.3k2.00
[PDF]GraphGuard: Graph-Constrained Neuro-Symbolic Synthesis of Network Defense Configurations▲3.0k2.33
Withdrawn or desk rejected (644)
[PDF]Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QAWithdrawn1.67
[PDF]Trace2Prog: Compiling and Calibrating Agent Experience into Reusable Visual ProgramsWithdrawn1.67
[PDF]SGRPO: Optimizing State-Space Language Models with State-Isolated Group-Relative PolicyWithdrawn1.00