Meta squared: Precomputing Reusable Knowledge for Online Harness Evolution in Long-Horizon Agents
cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/deepseek-ai/deepseek-harness
Project page: https://meta-square.github.io
Terminology
Sources
- Training-Free Group Relative Policy Optimization
- CHILL-Harness: Counterfactual Harness Learning for Efficient Reasoning in Long-Horizon Agents
- Read Before You Think: Mitigating LLM Comprehension Failures with Step-by-Step Reading
- ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
- DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
- Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance
- SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models
- Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
- Continual Harness: Online Adaptation for Self-Improving Foundation Agents
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Revealing Treatment Non-Adherence Bias in Clinical Machine Learning Using Large Language Models
- Local MDI+: Local Feature Importances for Tree-Based Models
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis
- Do Sparse Autoencoders Identify Reasoning Features in Language Models?
- TTHE: Test-Time Harness Evolution
- Code as Agent Harness
- Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents