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72 results for “keyword:"self improving"” in ICLR 2027. 11 withdrawn or desk rejected listed apart.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]When the Evaluator Changes: Measuring False Progress in Self-Improving Language Models▼5.8k2.33
[PDF]Skill Libraries Change What an Edit Does: When Should Agent Skill Validation Run In Context?▲3972.67
[PDF]AdaFleet: An Adaptive Orchestrator–Subagent Coevolution Framework for Efficient Quantitative Signal Discovery▼4.3k2.00
[PDF]VeriLoop Coder-E1: Toward Verifiable Recursive Self-Improvement through the VeriLoop Spiral▲11.00
[PDF]Guardrails Must Be Earned: Fabrication-Resistant Compilation of Failure Traces into Anti-Pattern Skills▲5103.00
[PDF]Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks▲3.0k2.33
[PDF]A HARNESS CAN REPLICATE AND STILL REGRESS: TASK-CONDITIONAL CAUSAL ADMISSION FOR SELF- IMPROVING AGENTS▼4.3k2.00
[PDF]On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification▼4.5k2.67
[PDF]From Practice to Model Weights: Consolidating the Skill Library of a Self-Improving LLM Agent into LoRA▼4.3k2.00
[PDF]Verify Less, Evolve More: Training Idea-Level Critics for Verification-Efficient ML Evolving Agents▼4.3k2.00
[PDF]If It Ain't Broke, Don't Fix It: Failures of Epistemic Control in Language-Model Agents▼4.3k2.00
[PDF]When Better Gets Worse: Improvement Fidelity for Self-Improving Agents in Adaptive Worlds▼1.2k1.67
[PDF]A Risk-Bounded Gate for Self-Improving Agents: Selecting Modifications as a Mean–Variance Knapsack▼1361.33
[PDF]A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering▲3.9k1.67
[PDF]Experience Is Not Enough: Knowledge-Grounded Evolutionary Search for AscendC Kernel Generation▼1.2k1.67
[PDF]Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents▲5103.00
[PDF]Forgetting is What to learn: Verifier-Grounded Minimal-Core Skills for Self-Evolving Agents▲3.0k2.33
[PDF]Verification Mirage: Mapping and Repairing the Reliability Boundary of Self-Verification in Medical VQA▲5103.00