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
112 results for “keyword:"scientific discovery"” in ICLR 2027. 21 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]If It Ain't Broke, Don't Fix It: Failures of Epistemic Control in Language-Model Agents▼4.3k2.00
[PDF]What Can Large Language Models Discover from Experiments? Scientific Claims and Discovery Value across Multiple Worlds▼1611.50
[PDF]Mechanistic Interpretability Findings That Generalize: Chaperone-Dependent Folding in ESMFold2▼4.3k2.00
[PDF]From Evidence to Action: Experience- and Knowledge-Grounded Evolution for Materials Discovery▼4.3k2.00
[PDF]HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses▼1361.33
[PDF]Do AI Agents Have Research Taste? SENSE-Bench for Anomaly-Driven Scientific Exploration▼1.2k1.67
[PDF]EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery▲3.8k2.50
[PDF]Exploring How LLM-Guided Scientific Discovery Can Find Solutions to Long-Standing Challenges in Disease Risk Prediction from Genetic Data▼1361.33
[PDF]Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space▲143.33
[PDF]CreativeBench2.0: Benchmarking Creative Method Discovery and Foresight Toward Recursive Self-Improvement▼4.5k2.67
[PDF]MELD: Recursive Self-Improvement via Hierarchical Coordination for Multi-Agent Scientific Discovery▲9.2k2.67
[PDF]SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery▼4.5k2.67
[PDF]SciDialect: Symbolic Compression as an Intrinsic Reward for Scientific Discovery Agents▲3.0k2.33
Withdrawn or desk rejected (21)
[PDF]ViGa-SR: LLM-based Evolutionary Search for Symbolic Regression with Visual Priors Guidance from Multimodal Representation of DataWithdrawn1.33
[PDF]Beyond Hypothesis Recovery: Evaluating Scientific Hypothesis Generation through Evidence-Hypothesis TransitionsWithdrawn1.33
[PDF]TadA-Bio: A Replayable Biomedical AI-Agent Benchmark for Budgeted Directed EvolutionWithdrawn1.67
[PDF]From Tools to Instruments: Tracking Measurement Uncertainty in Autonomous Science AgentsWithdrawn1.25