MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
cs.LG, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/QwenLM/qwencode
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality
- Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
- TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents
- AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
- Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
- Training Verifiers to Solve Math Word Problems
- HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- Mathematical exploration and discovery at scale
- Controlled Self-Evolution for Algorithmic Code Optimization
- DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
- AIDE: AI-Driven Exploration in the Space of Code
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Evolution through Large Models
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- Position: Agentic Evolution is the Path to Evolving LLMs
- EvoX: Meta-Evolution for Automated Discovery
- AutoHarness: improving LLM agents by automatically synthesizing a code harness
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks