# ReTerm: Recovery Training for Self-Improving Terminal Agents

arXiv: https://arxiv.org/abs/2610.18484 · HTML: https://mlsanity.com/paper/2610.18484/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 26 of 26)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents](https://mlsanity.com/paper/2504.07164/) (2025)
- [SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation](https://mlsanity.com/paper/2406.14991/) (2024)
- [Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback](https://mlsanity.com/paper/2506.03106/) (2025)
- [Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training](https://mlsanity.com/paper/2501.11425/) (2025)
- [Endless Terminals: Scaling RL Environments for Terminal Agents](https://mlsanity.com/paper/2601.16443/) (2026)
- [SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent](https://mlsanity.com/paper/2511.16108/) (2025)
- [On Data Engineering for Scaling LLM Terminal Capabilities](https://mlsanity.com/paper/2602.21193/) (2026)
- [LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces](https://mlsanity.com/paper/2602.14337/) (2026)
- [Tmax: A simple recipe for terminal agents](https://mlsanity.com/paper/2606.23321/) (2026)
- [TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents](https://mlsanity.com/paper/2602.07274/) (2026)
- [ECHO: Terminal Agents Learn World Models for Free](https://mlsanity.com/paper/2605.24517/) (2026)
- [Recursive Synthesis for Long-Horizon Terminal Tasks](https://mlsanity.com/paper/2608.05466/) (2026)
- [Exploring Reasoning Reward Model for Agents](https://mlsanity.com/paper/2601.22154/) (2026)
- [SETA: Scaling Environments for Terminal Agents](https://mlsanity.com/paper/2607.10891/) (2026)
- [OpenThoughts-Agent: Data Recipes for Agentic Models](https://mlsanity.com/paper/2606.24855/) (2026)
- [FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis](https://mlsanity.com/paper/2608.18580/) (2026)
- [T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks](https://mlsanity.com/paper/2609.11042/) (2026)

## Abstract (arXiv)

Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution (e.g., command errors, faulty implementations), eventually leading to task failures. To this end, we present ReTerm, a self-improving terminal agent trained by learning how to recover from its own failed terminal tasks. To support its training, we construct a customized data pipeline and produce ReTerm-10K, a high-quality dataset that provides effective recovery demonstrations for SFT cold start. Furthermore, we propose ReTerm-GRPO, an online RL algorithm that forks from the agent's own failure states to generate multiple independent self-recovery attempts. By learning from whether these attempts successfully complete the task, the agent self-improves through its own recovery experience. Built on Qwen3.5-9B, our ReTerm-9B achieves 34.8% Pass@1 on Terminal-Bench 2.0, improving over the base model by 14.6 points. Further analysis shows that our method achieves consistently higher recovery rates across diverse error categories compared with standard GRPO training. All code, data and model are released at https://github.com/twothsnd/ReTerm.