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
454 results for “keyword:"evolution"” in ICLR 2027. 119 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Beyond Initial Skills: Contrast-Guided Skill Evolution for Robust Learning in LLM Agents▼5.8k2.33
[PDF]What Should the Reflector See? An Empirical Study of Evidence in Reflective Prompt Optimization▼1351.33
[PDF]SM2-AHD: Search Experience Memory and Meta-Cognitive Reflection for LLM-Based Automatic Heuristic Design▼1351.33
[PDF]Continual-Skill: Utility Optimization-Driven Co-Evolution of Policies and Skill Libraries▼4.3k2.00
[PDF]Unified Hierarchical Red-Teaming: Strategy Search and Evidence-Guided Policy Evolution▼4.3k2.00
[PDF]SynKer: Synthesize, Kernelize, Reinforce - Teaching GPU Kernel Generation to Small Language Models▼5.8k2.33
[PDF]From Teacher Imitation to Failure Diagnosis: Causality-Inspired Test-Time Evolution of Small Language Models with LLM Feedback▼1.2k1.67
[PDF]Geometric Regularization of Learned Behavior Spaces in Unsupervised Quality-Diversity Optimization▼5.8k2.33
[PDF]Query Complexity of Forward-Only Hebbian Learning: Theory and a Native Fit for Diffusion Models▼4.3k2.00
[PDF]Two-Time-Scale Weight Adaptation and Evolutionary Genome Search for Pareto Front Coverage▼1.2k3.00
[PDF]GPU Forecasters: Language Models as Speculative Surrogates for Kernel Runtime Optimization▼4.3k2.00
[PDF]MuseDrift: Navigating Protein Evolutionary Manifolds with Conditional Discrete Diffusion▼4.3k2.00
Withdrawn or desk rejected (119)
[PDF]ViGa-SR: LLM-based Evolutionary Search for Symbolic Regression with Visual Priors Guidance from Multimodal Representation of DataWithdrawn1.33
[PDF]Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy LearningDesk rejected
[PDF]VideoEvoHarness: Self Evolving Agent Harness from Unlabeled Videos for Video UnderstandingWithdrawn1.75
[PDF]From Agent Harnesses to COP Experts: Automated Skill Evolution for Cross-Problem Combinatorial OptimizationDesk rejected