arXiv cs.AI· Xi Qin, Isabel Kurth, Xin Cui, Elin Park, Alexander Schaefer, Yaad Oren·· 4 小时前AI 评分47
终端智能体训练为何停滞:数据生成与验证挑战解析
When Terminal-Agent Training Stalls: Demystifying Data Generation and Verification Challenge
AI 导读
一项研究用自动生成容器化终端任务及可执行验证器的流水线,拆解了任务生成与实时环境评估中的失败模式,区分结构有效性、验证器忠实度、策略可解性与基础设施可靠性四项要求。
正文 · 原文
Abstract:Automated terminal-agent training relies on generated environments and verifiers to turn open-ended interaction into reward. Yet a runnable Docker image and executable test suite do not guarantee that the resulting reward is faithful, informative, or even attributable to agent behavior. We present a pipeline that generates containerized terminal tasks and their executable verifiers, and use it to demystify failure modes in task generation and live-environment evaluation. Our analysis separates four requirements that are often conflated: structural validity, verifier faithfulness, policy solvability, and infrastructure reliability. In a GRPO training of Qwen3.5-9B, it overfits on a relatively easy dataset within 20 steps. Conversely, in a controlled Qwen3.5-9B comparison, adding hard tasks lowers mean rollout pass@2 from 81.3% to 20.6%, restoring informative failures without changing the training configuration. We further identify near-duplicate task generation, incomplete anti-shortcut safeguards, Dockerfile failures, asynchronous pass@k bias, and concurrency-induced environment errors as distinct threats to measurement. These findings should motivate the community for a terminal agent specific evaluation harness that pairs structural checks and rollout-derived solvability with extensive verifier audits.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.02405 [cs.AI] |
| (or arXiv:2610.02405v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02405 arXiv-issued DOI via DataCite |
Submission history
From: Xi Qin [view email]
[v1]
Thu, 1 Oct 2026 19:32:44 UTC (81 KB)
[v2]
Mon, 16 Nov 2026 19:59:00 UTC (82 KB)
来源:arXiv cs.AI · arxiv.org