# Can Terminal Agents Trust Their Own Verification? Diagnosing and Improving Self-Verification

arXiv: https://arxiv.org/abs/2609.38812 · HTML: https://mlsanity.com/paper/2609.38812/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 55 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [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-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning](https://mlsanity.com/paper/2502.12853/) (2025)
- [Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments](https://mlsanity.com/paper/2602.01244/) (2026)
- [TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents](https://mlsanity.com/paper/2602.07274/) (2026)
- [Learning to Self-Verify Makes Language Models Better Reasoners](https://mlsanity.com/paper/2602.07594/) (2026)
- [Dream-RSI: Recursive Self-Improvement through Evolving Worlds](https://mlsanity.com/paper/2609.14858/) (2026)
- [Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs](https://mlsanity.com/paper/2509.14257/) (2025)
- [Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents](https://mlsanity.com/paper/2602.07900/) (2026)
- [Structured Agent Distillation for Large Language Model](https://mlsanity.com/paper/2505.13820/) (2025)
- [Failure as a Process: An Anatomy of CLI Coding Agent Trajectories](https://mlsanity.com/paper/2607.09510/) (2026)
- [SETA: Scaling Environments for Terminal Agents](https://mlsanity.com/paper/2607.10891/) (2026)
- [Scaling Agentic Verifier for Competitive Coding](https://mlsanity.com/paper/2602.04254/) (2026)
- [SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review](https://mlsanity.com/paper/2607.06065/) (2026)
- [What Resolve Rate Hides: Trajectory Structure Diagnostics for Coding Agents](https://mlsanity.com/paper/2607.06184/) (2026)
- [SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?](https://mlsanity.com/paper/2605.22175/) (2026)
- [Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes](https://mlsanity.com/paper/2607.19843/) (2026)
- [Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework](https://mlsanity.com/paper/2608.08950/) (2026)

## Abstract (arXiv)

Terminal agents rely on self-verification to assess and correct their solutions as they solve tasks through interaction with command-line environments. Yet how trustworthy such self-verification is remains poorly understood. To investigate this question systematically, we introduce a diagnostic framework that identifies the first complete solution in each trajectory, determines whether it is objectively correct, and uses this ground truth to quantify the agent's subsequent verification and recovery behavior. Applying it to ten terminal agents on TerminalBench2.1, we find that verification is nearly universal after a complete candidate is formed, yet only 61.43% of incorrect candidates are detected and only 49.36% of detected errors are successfully repaired. These results show that the main weakness in self-verification lies not in initiating verification, but in detecting and repairing errors. Motivated by these findings, we propose Student-Conditioned Verification Distillation (SCVD), which lets the student first produce a candidate solution and distills a stronger teacher's subsequent verification and recovery from the same interaction context. Across three Qwen3.5 backbones, SCVD improves textscPass@1 on TerminalBench2.1 by 9.74--16.85 percentage points over the corresponding base models and by 4.49--8.61 points over the standard full-trajectory distillation, while avoiding the pronounced out-of-distribution degradation of full-trajectory distillation on SWE-bench Verified.