Abstract:Modern AI agents increasingly combine conversational interaction with autonomous task execution, such as coding and web research, raising a natural question: What happens when an agent engaged in long-horizon tasks is exposed to user persuasion? Yet studying this possibility is challenging because long-running agent behavior is noisy and costly to reproduce, and it remains unclear which unique challenges emerge only in extended task execution. We study how belief-level intervention can influence downstream task behavior, a phenomenon we name persuasion propagation. We introduce a behavior-centered evaluation framework that distinguishes between persuasion applied during or prior to task execution. Across web research and coding tasks, we find that on-the-fly persuasion induces weak and inconsistent behavioral effects. In contrast, when the belief state is explicitly specified at task time, belief-prefilled agents conduct on average 26.9% fewer searches and visit 16.9% fewer unique sources than neutral-prefilled agents. These results suggest that persuasion, even in prior interaction, can affect the agent's behavior, motivating behavior-level evaluation in agentic systems.
| Comments: | Code available at this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2602.00851 [cs.AI] |
| (or arXiv:2602.00851v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2602.00851 arXiv-issued DOI via DataCite |
From: Hyejun Jeong [view email]
[v1]
Sat, 31 Jan 2026 18:33:14 UTC (4,291 KB)
[v2]
Sun, 15 Feb 2026 22:45:36 UTC (4,291 KB)
[v3]
Thu, 21 May 2026 00:39:39 UTC (4,288 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。