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
149 results for “keyword:"mathematical reasoning"” in ICLR 2027. 22 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Predicting Reasoning Errors Before They Occur: A Prompt-Side Activation Direction Anticipates Correctness in a Large Language Model▼1361.33
[PDF]Beyond Semantic Similarity: Abstraction-Based Demonstration Retrieval for Mathematical Reasoning▼5.8k2.33
[PDF]Bidirectional Transfer, Asymmetric Expression: Math Fine-Tuning Conceals the Code Gains It Carries▲13k2.33
[PDF]Probing the Emergent Global Workspace of Reasoning Models on Structured Reasoning Tasks▲9.2k2.67
[PDF]Compress to Improve: Reclaiming Output Budget from On-Policy Distillation for Stronger Reasoning▼1.2k1.67
[PDF]Knowing When to Stop: IGP-Bench and the Multi-Agent System GALOIS for the Inverse Galois Problem▼4.3k2.00
[PDF]The Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence▼4.3k2.00
[PDF]Mathematica Incognita: Characterizing Open-Ended Mathematical Exploration in Language Models▲9.2k2.67
[PDF]PictureProof: Evaluating Mathematical Reasoning in Vision-Language Models with Visual Proofs▲5103.00
[PDF]The Solution Is the Supervision: Learning to Verify Reasoning without Human Step Labels▼5.8k2.33
[PDF]Accuracy Is Not Enough: Measuring Instruction-Following Stability Under Post-Training Quantization▲11.00
[PDF]EnergyOPD: Energy-Based On-Policy Distillation for Stable and Generalizable Knowledge Transfer▲3.0k2.33
[PDF]When Clipping Becomes a Learning Signal: A Permutation Baseline for Policy Optimization▲3.0k2.33
[PDF]Tracing Error Origins and Propagation: Dependency-Grounded Process Supervision for Mathematics and Physics▲6.1k2.00
[PDF]Scoring the Same Outputs: How Answer-Extractor Choice and Consistency Change Benchmark Comparisons▼1361.33
[PDF]STRATA: Preserving Rare Solution Strategies in Reinforcement Learning with Verifiable Rewards▼1361.33
[PDF]When LoRA Rank Matters in RLVR: Saturation-Gated Scaling and Off-Principal Initialization▼1361.33
[PDF]Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL▲5103.00
[PDF]Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation Steering▼4.3k2.00
[PDF]From Self-Correction to Self-Evolution: Agentic Test-Time Learning for Mathematical Reasoning▼4.3k2.00
Withdrawn or desk rejected (22)
[PDF]Are We Ready for Proof Weaving? Understanding Agent Swarms through Fermat's Last TheoremWithdrawn1.67
[PDF]T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement LearningWithdrawn1.33
[PDF]The Underdetermined Stream: What a Single-Gold Score Actually Measures on Contested MaterialWithdrawn1.67
[PDF]An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical ProblemsWithdrawn2.00