# Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite

arXiv: https://arxiv.org/abs/2610.02826 · HTML: https://mlsanity.com/paper/2610.02826/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 30 of 31)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [R-Zero: Self-Evolving Reasoning LLM from Zero Data](https://mlsanity.com/paper/2508.05004/) (2025)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [Self-Harness: Harnesses That Improve Themselves](https://mlsanity.com/paper/2606.09498/) (2026)
- [SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization](https://mlsanity.com/paper/2604.02268/) (2026)
- [AutoHarness: improving LLM agents by automatically synthesizing a code harness](https://mlsanity.com/paper/2603.03329/) (2026)
- [Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows](https://mlsanity.com/paper/2605.27922/) (2026)
- [Rethinking the Evaluation of Harness Evolution for Agents](https://mlsanity.com/paper/2607.12227/) (2026)
- [VisPlay: Self-Evolving Vision-Language Models from Images](https://mlsanity.com/paper/2511.15661/) (2025)
- [Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading](https://mlsanity.com/paper/2607.08964/) (2026)
- [MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data](https://mlsanity.com/paper/2603.09206/) (2026)
- [Recursive Synthesis for Long-Horizon Terminal Tasks](https://mlsanity.com/paper/2608.05466/) (2026)
- [Dream-RSI: Recursive Self-Improvement through Evolving Worlds](https://mlsanity.com/paper/2609.14858/) (2026)
- [AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces](https://mlsanity.com/paper/2608.23041/) (2026)
- [The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation](https://mlsanity.com/paper/2607.22585/) (2026)
- [Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences](https://mlsanity.com/paper/2609.24965/) (2026)
- [ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement](https://mlsanity.com/paper/2609.14857/) (2026)
- [AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses](https://mlsanity.com/paper/2608.12307/) (2026)
- [ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents](https://mlsanity.com/paper/2609.17523/) (2026)
- [Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection](https://mlsanity.com/paper/2608.20169/) (2026)
- [SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness](https://mlsanity.com/paper/2609.20519/) (2026)
- [Harness-Zero: Harness Distillation via Agent-as-Harness](https://mlsanity.com/paper/2609.24974/) (2026)
- [Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails](https://mlsanity.com/paper/2609.09134/) (2026)
- [DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds](https://mlsanity.com/paper/2608.06113/) (2026)
- [PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning](https://mlsanity.com/paper/2607.21419/) (2026)
- [StateM: Reaching 95.3% Raw Accuracy, or a 15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling](https://mlsanity.com/paper/2608.15089/) (2026)

## Built on by (most cited first, 1 of 1)

- [Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress](https://mlsanity.com/paper/2610.14146/) (2026)

## Abstract (arXiv)

Successful trajectories on difficult tasks provide valuable supervision for model improvement, but specialized harnesses introduce interventions that may be unavailable during deployment. We propose Recursive Self-Rewrite (RSR), a framework that uses one base model, Qwen-3.8-27B, to discover successful solutions under diverse harnesses and reconstruct them as training trajectories under a general harness. A planner extracts procedures into runbooks, a critic screens for verifier and solution leakage and guides recursive revision, and an executor follows qualified runbooks in fresh sandboxes. Across approximately 3K self-curated terminal tasks, three harnesses jointly solve 759 tasks, 34.3% more than the strongest individual harness in the recorded pool. RSR expands 2,001 successful source trajectories into 11,094 rewritten trajectories for supervised finetuning. Training on these trajectories outperforms both the base model and direct trajectory SFT. Compared with the base model, pass@3 increases from 57.0% to 74.2% on Terminal-Bench 2, from 1.5% to 9.1% on Terminal-Bench 4, from 39.0% to 63.0% on our self-curated Terminal-Bench Hard, and from 3.0% to 6.0% on our Software Terminal-Bench. Process reward on Long-Horizon Terminal-Bench rises from 0.21 to 0.29. These results show how diverse harness-assisted experiences can be reconstructed into reusable capabilities for a model operating under a general harness.