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
29 results for “keyword:"scientific reasoning"” in ICLR 2027. 7 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences▼4.3k2.00
[PDF]Discover-Many-Worlds: Reinforcement Learning for Scientific Discovery in Automatically Generated Physics▼4.5k2.67
[PDF]A Video Question Answering Dataset for Validating Understanding of Scientific Goal-Directed Cognition▲6.1k2.00
[PDF]CataPath: Expert-Augmented Path Search for Constraint-Aware Scientific Reasoning in Catalyst Design▼5.8k2.33
[PDF]Before the First Equation: Selective Scene Control in Large Language Model Physics Reasoning▼4.3k2.00
[PDF]How Stable Are Answers to Unresolved Scientific Questions? Separating Repeat Variability from Input Sensitivity▼1.2k1.67
[PDF]What Can Large Language Models Discover from Experiments? Scientific Claims and Discovery Value across Multiple Worlds▼1611.50
[PDF]What Should We Work on Next? Node-Level Compute Allocation Across Open Scientific Questions▲9.2k2.67
[PDF]BioTraceBench: Evaluating Computational Execution and Evidence-Based Reasoning in Biomedical Research▲13k2.33
[PDF]CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation▼5.8k2.33
[PDF]Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific Reasoning▲3.0k2.33
Withdrawn or desk rejected (7)
[PDF]LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward ModelsWithdrawn1.67
[PDF]SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?Withdrawn1.67