Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- A General Language Assistant as a Laboratory for Alignment
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Constitutional AI: Harmlessness from AI Feedback
- Safe RLHF: Safe Reinforcement Learning from Human Feedback
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories
- Meta-Harness: End-to-End Optimization of Model Harnesses
- ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
- Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
- A Self-Improving Coding Agent
- Identifying the Risks of LM Agents with an LM-Emulated Sandbox
- Reflexion: Language Agents with Verbal Reinforcement Learning
- AdaPlanner: Adaptive Planning from Feedback with Language Models
- BaxBench: Can LLMs Generate Correct and Secure Backends?
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- ThetaEvolve: Test-time Learning on Open Problems
- SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM 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