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
72 results for “keyword:"self improving"” in ICLR 2027. 11 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]MELD: Recursive Self-Improvement via Hierarchical Coordination for Multi-Agent Scientific Discovery▲9.2k2.67
[PDF]The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures▼1.2k1.67
[PDF]What Did the Agent Learn From? Cross-Episode Memory Attribution for Self-Improving Agents▲3.0k2.33
[PDF]GrokRSI: Few-Shot Agentic Recursive Self-Improvement Through Qualified Task–Harness Co-Evolution▼4.3k2.00
[PDF]Self-Improvement Needs Attribution: Dependency-Aware Causal Memory for Long-Horizon Mobile GUI Agents▼1.2k3.00
[PDF]Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents▼5.8k2.33
Withdrawn or desk rejected (11)
[PDF]OPTScientist: Toward Recursive Self-Improving Agents via Automated Optimizer DiscoveryWithdrawn1.33
[PDF]What to Learn, What to Keep: Information-Guided Sampling and Text-Space Weight Decay for Self-Evolving Agent SkillsDesk rejected
[PDF]Self-improving Semi-supervised Medical Image Segmentation via Consensus-enhanced Prototype-prompted Segment Anything ModelWithdrawn1.67
[PDF]TABRSI: A RECURSIVE SELF-IMPROVING MULTI- AGENT SYSTEM FOR TABLE UNDERSTANDING AND REASONINGWithdrawn1.50