Harness-Zero: Harness Distillation via Agent-as-Harness

arXiv:2609.24974 · cs.AI, cs.CL, cs.NE · Submitted 2026-09-21 · Read on arXiv

cs.AI, cs.CL, cs.NE

Submitted: 2026-09-21

Updated: 2026-09-21

Code: https://github.com/metaevo-ai/harness-zero

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 30× in this paper · explained in 2 episodes
• Adaptation — 20× in this paper · explained in 1 episode
• Action Space — 18× in this paper · explained in 1 episode
• Verification — 16× in this paper · explained in 2 episodes
• Agent Harness — 12× in this paper · explained in 2 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Verifier — 6× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Grounding — 2× in this paper · explained in 3 episodes
• Provenance — 2× in this paper · explained in 3 episodes
• Scaffolding — 2× in this paper · explained in 3 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Agentic Evaluation — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Online Adaptation — 1× in this paper · explained in 3 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• Progressive Disclosure — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
• HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
• Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
• SIA: Self Improving AI with Harness & Weight Updates
• Continual Harness: Online Adaptation for Self-Improving Foundation Agents
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
• WHALE: A Simple Recipe for Joint Harness-Weight Optimization
• Kimi K3: Open Frontier Intelligence
• What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents
• Meta-Harness: End-to-End Optimization of Model Harnesses
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
• More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding
• Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
• HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection