Learning from Research: Toward Lifelong Agent Harness Evolution
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/UCSB-NLP-Chang/ScholarEvolve
Terminology
Sources
- Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents
- Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents
- CodeMonkeys: Scaling Test-Time Compute for Software Engineering
- Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
- Accelerating scientific discovery with Co-Scientist
- Better Prompt Compression Without Multi-Layer Perceptrons
- Evo-Bench: Can Language Models Improve Agent Harness?
- Continual Harness: Online Adaptation for Self-Improving Foundation Agents
- Towards a Science of Scaling Agent Systems
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
- How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
- Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
- AutoHarness: improving LLM agents by automatically synthesizing a code harness
- CAST: Character-and-Scene Episodic Memory for Agents
- Code as Agent Harness
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