arXiv cs.CL· Mingyu Chen, Jingkai Lin, Xiaofen Xing, Liankai Huang, Ruiqi Xiong, Xiangmin Xu·· 11 小时前AI 评分38
大语言模型能否将智能体能力扩展到开放式多轮对话的目标追求？
Can Large Language Models Extend Their Agentic Capabilities to Goal Pursuit in Open-Ended Multi-Turn Interaction?
AI 导读
研究提出 Tool-Mediated Interaction（TMI）协议，将对话动作表示为工具调用、对方回应表示为工具结果，无需训练即可维持推理-行动-观察循环。
正文 · 原文
Abstract:Goal pursuit in open-ended dialogue requires agents to adapt their actions to interaction feedback across successive exchanges. We investigate whether agentic capabilities developed for multi-step tool use carry over to dialogue organized through the model's native tool interface, and how this changes interaction behavior. We define Tool-Mediated Interaction (TMI) as a training-free protocol that represents dialogue actions as tool calls and counterpart responses as tool results, maintaining a continuous reasoning-action-observation loop with retained reasoning and interaction history. We evaluate TMI across social interaction, emotional support, persuasion, and price negotiation using two models and 15,678 main-experiment episodes. Across both models, TMI improves social goal attainment, emotional-support preference, donation amounts, and buyer negotiation margins over conversational baselines with and without thinking. A Qwen ablation further shows that TMI outperforms ordinary conversation with retained reasoning on all four primary outcomes. Behavioral analyses associate the improvements with task-specific patterns in initial proposals and responses to interaction feedback. Alongside these gains, TMI reduces mean reasoning tokens per decision by 42.0-81.5% relative to the thinking baseline and lowers mean cross-turn phrase reuse across all eight model-environment pairs. These findings show that interaction organization shapes both goal attainment and reasoning across dialogue turns.
| Comments: | 18 pages, 9 figures, 20 tables, including appendices |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.01552 [cs.CL] |
| (or arXiv:2611.01552v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01552 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mingyu Chen [view email]
[v1]
Sun, 1 Nov 2026 04:23:27 UTC (814 KB)
来源：arXiv cs.CL · arxiv.org