ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

arXiv:2609.14857 · cs.CL · Submitted 2026-09-14 · Read on arXiv

cs.CL

Submitted: 2026-09-14

Updated: 2026-09-14

Code: https://github.com/IQuestLab/ModularRSI

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

Terminology

• Benchmark — 37× in this paper · explained in 2 episodes
• Accuracy — 16× in this paper · explained in 1 episode
• Foundation Model — 11× in this paper · explained in 3 episodes
• Foundation Models — 10× in this paper · explained in 7 episodes
• Adaptation — 6× in this paper · explained in 1 episode
• Trace — 6× in this paper · explained in 2 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Generalization — 5× in this paper · explained in 13 episodes
• Recursive Self-Improvement — 3× in this paper
• Redundancy — 3× in this paper · explained in 2 episodes
• AI Agents — 2× in this paper · explained in 2 episodes
• Agent Harness — 2× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 4 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• State Management — 1× in this paper · explained in 3 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
• HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
• Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• Living-Harness Is an Interactive-Agent Evolver
• Endless Terminals: Scaling RL Environments for Terminal Agents
• Meta-Harness: End-to-End Optimization of Model Harnesses
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
• AutoHarness: improving LLM agents by automatically synthesizing a code harness
• HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution
• Learning from the Self-future: On-policy Self-distillation for dLLMs
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• Recursive Self-Evolving Agents via Held-Out Selection
• Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
• S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
• MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection
• Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
• HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
• Aspire: Can Models Self-Evolve from Vague Goals?

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering