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2,521 results for “keyword:"reasoning"” in ICLR 2027. 644 withdrawn or desk rejected listed apart.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]LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforcement Learning▲3922.67
[PDF]VideoTapestry: Query-Adaptive Memory Refinement for Multi-Agent Long-Video Understanding▼5.8k2.33
[PDF]DepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language Models▼5.9k2.50
[PDF]PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination▲8042.80
[PDF]Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers▲3.0k2.33
[PDF]TokenDistill: Compressing CoT via Iterative Token Distillation with Continuous Prompt Transformation▼1.2k1.67
[PDF]AffToM: Benchmarking Recursive Affective Theory of Mind in Dynamic Multi-Party Interactions▲4.6k3.00
[PDF]Train for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning▲1.7k3.33
[PDF]DACPO: Drift-Adaptive Constrained Policy Optimization for Cue-Free Safety Recovery in Large Reasoning Models▲3922.67
[PDF]DocTrek: Tree-Guided Agentic Reinforcement Learning via Dense Rewards for Document Understanding▼4.3k2.00
[PDF]LinAlg-Bench: When LLMs Stop Computing — Structured Hallucination, Sign Drift, and Depth-Gated Collapse in Matrix Arithmetic▲11.00
[PDF]When Is Program Structure Required? Certificate-Grounded Calibration of Program-Induction Difficulty▼5.8k2.33
[PDF]Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision–Language Models▲2843.00
[PDF]Trace Before You Conclude: Learning Evidential Reasoning for Industrial Maintenance Report Generation▼4.3k2.00
[PDF]Physiology as Topology: Intervenable Organ Graphs for Longitudinal Patient Forecasting▼1.3k1.75
[PDF]LODGE: A CONVERSATIONAL TRAVEL AGENT BENCHMARK WITH GROUNDED GOALS AND CONTROLLABLE DIFFICULTY▲3922.67
[PDF]ECLIPSE: An Executable Contextual Intervention and Planning Agent for Time-Series Tasks▼4.3k2.00
Withdrawn or desk rejected (644)
[PDF]NeuroFORM: Neuro-Symbolic Formalization of Legal Rules with Counterexample-Guided RefinementWithdrawn2.00
[PDF]ReLoC: Recursive Local Causal Modeling for Explaining and Predicting LLM-Based Multi-Agent BehaviorWithdrawn1.33
[PDF]Retrieval-Augmented Anatomy-Aware Reasoning for Interpretable Alzheimer's DiagnosisWithdrawn1.33
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33