SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

arXiv:2609.20519 · cs.AI · Submitted 2026-09-17 · Read on arXiv

cs.AI

Submitted: 2026-09-17

Updated: 2026-09-17

Comments: 15 pages, 8 figures, 4 tables. Code: https://github.com/NVlabs/SoL-Pi . Project page: https://nvlabs.github.io/SoL-Pi/

Code: https://github.com/NVlabs/SoL-Pi

Project page: https://nvlabs.github.io/SoL-Pi

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

Terminology

• Benchmark — 44× in this paper · explained in 2 episodes
• Agent Harness — 19× in this paper · explained in 2 episodes
• Verifier — 8× in this paper · explained in 2 episodes
• Verification — 7× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Quantization — 3× in this paper · explained in 12 episodes
• Scaling Laws — 3× in this paper · explained in 4 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Elias — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Analyzer — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Humanize Olympic Agents — 1× in this paper
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Evaluating Large Language Models Trained on Code
• Measuring AI Ability to Complete Long Software Tasks
• The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
• Hyperagents
• AgentFold: Long-Horizon Web Agents with Proactive Context Management
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• RouteLLM: Learning to Route LLMs with Preference Data
• Meta-Harness: End-to-End Optimization of Model Harnesses
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
• Recursive Harness Self-Improvement
• Rethinking the Evaluation of Harness Evolution for Agents
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• Code as Agent Harness
• Recursive Agent Harnesses
• AutoHarness: improving LLM agents by automatically synthesizing a code harness
• MemoHarness: Agent Harnesses That Learn from Experience
• LLM-as-Code: Agentic Programming for Agent Harness
• ACON: Optimizing Context Compression for Long-horizon LLM Agents
• Scaling Long-Horizon LLM Agent via Context-Folding

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