When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents less than 1 minute read Published: August 31, 2026
Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification less than 1 minute read Published: August 31, 2026
Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets less than 1 minute read Published: August 31, 2026
How to Guide LLM Generation: Dual-Surrogate Guided Search for Automated Heuristic Design less than 1 minute read Published: August 31, 2026
StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments less than 1 minute read Published: August 31, 2026
Coalition-Aware Skill Reliability for Self-Evolving Agents less than 1 minute read Published: August 31, 2026
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses less than 1 minute read Published: August 31, 2026
Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses less than 1 minute read Published: August 31, 2026
Evo-Bench: Can Language Models Improve Agent Harness? less than 1 minute read Published: August 31, 2026
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization less than 1 minute read Published: August 31, 2026
HELIX: Model-Harness Co-evolution for Recursive Self-Improvement less than 1 minute read Published: August 31, 2026
DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations less than 1 minute read Published: August 31, 2026
ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution less than 1 minute read Published: August 31, 2026
PostTrainBench: Can LLM Agents Automate LLM Post-Training? less than 1 minute read Published: August 25, 2026
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development? less than 1 minute read Published: August 12, 2026
Meta-Harness: End-to-End Optimization of Model Harnesses less than 1 minute read Published: August 09, 2026