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
198 results for “keyword:"self improvement"” in ICLR 2027. 52 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering▲3952.67
[PDF]In-MANU: Probing the Capabilities and Self-Improvement of Frontier Agents in Robotic Manipulation▼5.8k2.33
[PDF]RSIBench-Code: Can LLM Agents Handle Enterprise-Level LLM Development Code for Self-Improvement?▲3952.67
[PDF]HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance–Cost Trade-offs▼4.5k2.67
[PDF]Bilevel Incentive Optimization for Language Model Self-Improvement without Human Labels▼1.2k1.67
[PDF]Discovered, Not Designed: Population Evolution for Collaborative and Compute-Intensive Model Discovery▲3.0k2.50
[PDF]Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency▲3.0k2.33
[PDF]Self-Evolution Should Be Stable, Not Frozen: Lyapunov-Gated Recursive Self-Improvement▼4.3k2.00
[PDF]Train Ahead, Distill Back: Bootstrapping On-Policy Self-Distillation for Large Language Models▲3952.67
[PDF]Seeds Teach Each Other Through Prompt Tokens: Reward-Free Compositional Text-to-Image Self-Improvement▼5.8k2.33
[PDF]Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution▼4.3k2.00
[PDF]G\"odel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement▼4.3k2.00
Withdrawn or desk rejected (52)
[PDF]GymHarness: Recursive Self-Improvement of Agents with Recursively Verified VerifiersWithdrawn1.67