arXiv cs.CL· Minhyeon Oh, Chiyeong Heo, Geonwoo Noh, Hoyoung Kim, Jangwon Son, Jungseul Ok·· 12 小时前AI 评分52
BlackSwan：用猜想与反驳验证语言模型智能体的动作
Action Verification through Conjecture and Refutation for Language Model Agents
AI 导读
论文提出 BlackSwan，一种面向语言模型智能体的反驳式动作验证流程：先预测每个会改变状态的动作的预期效果，再构造可检验的出错假设，用已有观察或额外的非变更动作来检验，只有没有任何假设成立时才执行该动作。
正文 · 原文
Abstract:Language model agents increasingly act on users' behalf by manipulating external environments through tools, often from high-level instructions that leave critical task- and environment-specific context unstated. To prevent resulting misaligned actions, recent work verifies proposed actions before execution, largely by establishing whether the conditions supporting them hold. We argue that this confirmation-oriented view leaves a fundamental blind spot: a wrong action often passes every check that asks whether it is right. This motivates a different question for verification: rather than asking what evidence supports an action, can the agent find evidence that refutes it? We pursue this direction with BlackSwan, a refutation-oriented, expect-suspect-test procedure that predicts the intended effect of each state-mutating action, formulates specific and empirically testable hypotheses for how it could be wrong, and tests them using existing observations or additional non-mutating actions, executing the action only if none survives testing. On challenging AppWorld tasks, BlackSwan improves success rate over the strongest baseline by 14.9 and 25.2%p with and without the backbone model's thinking mode, respectively. Even without thinking or in-context demonstrations, it outperforms stronger baselines equipped with them. The gains also transfer beyond AppWorld, with BlackSwan improving WebShop performance by 12.7%p. More broadly, our results suggest that language model agents have an underused capacity to recognize and self-correct misaligned actions, which can be systematically elicited through active conjecture and refutation before execution.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.02950 [cs.AI] |
| (or arXiv:2611.02950v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.02950 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Minhyeon Oh [view email]
[v1]
Mon, 2 Nov 2026 11:15:40 UTC (420 KB)
来源：arXiv cs.CL · arxiv.org