Harness 2: Recursive Agent Harnessing for an Open World
cs.AI, cs.CL, cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/google-research/harness2
Sources
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
- MemoHarness: Agent Harnesses That Learn from Experience
- Harness Continual Learning: Continual Adaptation Beyond Model Parameters
- Continual Harness: Online Adaptation for Self-Improving Foundation Agents
- Recursive Harness Self-Improvement
- JobBench: Aligning Agent Work With Human Will
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
- EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement
- TTHE: Test-Time Harness Evolution
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
- Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories
- Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
- Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
- Rethinking the Evaluation of Harness Evolution for Agents
- MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill 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
- 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