Towards Direct Evaluation of Harness Optimizers via Priority Ranking
cs.AI
Submitted: 2026-05-21
Updated: 2026-10-06
Code: https://github.com/SWE-agent/mini-swe-agent
Sources
- SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?
- Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization
- Self-Evolving Search Index
- Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
- ReCreate: Reasoning and Creating Domain Agents Driven by Experience
- Automated Design of Agentic Systems
- AFlow: Automating Agentic Workflow Generation
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
- VeRO: A Harness for Agents to Optimize Agents
- Hyperagents
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Large Language Models Are Self-Taught Reasoners: Enhancing LLM Applications via Tailored Problem-Solving Demonstrations
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- ThetaEvolve: Test-time Learning on Open Problems
- Dr. Zero: Self-Evolving Search Agents without Training Data
- CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
- ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
- RobustFlow: Towards Robust Agentic Workflow Generation
- FlowReasoner: Reinforcing Query-Level Meta-Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems