WHEN TO ACT, WHEN TO WAIT: Modeling the Intent-Action Alignment Problem in Dialogue
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916912910303232 |
|---|---|
| author | Qian, Yaoyao Huang, Jindan Wang, Yuanli Yu, Simon Zhou, Kyrie Zhixuan Mao, Jiayuan Liang, Mingfu Zhou, Hanhan |
| author_facet | Qian, Yaoyao Huang, Jindan Wang, Yuanli Yu, Simon Zhou, Kyrie Zhixuan Mao, Jiayuan Liang, Mingfu Zhou, Hanhan |
| contents | Dialogue systems often fail when user utterances are semantically complete yet lack the clarity and completeness required for appropriate system action. This mismatch arises because users frequently do not fully understand their own needs, while systems require precise intent definitions. This highlights the critical Intent-Action Alignment Problem: determining when an expression is not just understood, but truly ready for a system to act upon. We present STORM, a framework modeling asymmetric information dynamics through conversations between UserLLM (full internal access) and AgentLLM (observable behavior only). STORM produces annotated corpora capturing trajectories of expression phrasing and latent cognitive transitions, enabling systematic analysis of how collaborative understanding develops. Our contributions include: (1) formalizing asymmetric information processing in dialogue systems; (2) modeling intent formation tracking collaborative understanding evolution; and (3) evaluation metrics measuring internal cognitive improvements alongside task performance. Experiments across four language models reveal that moderate uncertainty (40-60%) can outperform complete transparency in certain scenarios, with model-specific patterns suggesting reconsideration of optimal information completeness in human-AI collaboration. These findings contribute to understanding asymmetric reasoning dynamics and inform uncertainty-calibrated dialogue system design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01881 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WHEN TO ACT, WHEN TO WAIT: Modeling the Intent-Action Alignment Problem in Dialogue Qian, Yaoyao Huang, Jindan Wang, Yuanli Yu, Simon Zhou, Kyrie Zhixuan Mao, Jiayuan Liang, Mingfu Zhou, Hanhan Artificial Intelligence Computation and Language Dialogue systems often fail when user utterances are semantically complete yet lack the clarity and completeness required for appropriate system action. This mismatch arises because users frequently do not fully understand their own needs, while systems require precise intent definitions. This highlights the critical Intent-Action Alignment Problem: determining when an expression is not just understood, but truly ready for a system to act upon. We present STORM, a framework modeling asymmetric information dynamics through conversations between UserLLM (full internal access) and AgentLLM (observable behavior only). STORM produces annotated corpora capturing trajectories of expression phrasing and latent cognitive transitions, enabling systematic analysis of how collaborative understanding develops. Our contributions include: (1) formalizing asymmetric information processing in dialogue systems; (2) modeling intent formation tracking collaborative understanding evolution; and (3) evaluation metrics measuring internal cognitive improvements alongside task performance. Experiments across four language models reveal that moderate uncertainty (40-60%) can outperform complete transparency in certain scenarios, with model-specific patterns suggesting reconsideration of optimal information completeness in human-AI collaboration. These findings contribute to understanding asymmetric reasoning dynamics and inform uncertainty-calibrated dialogue system design. |
| title | WHEN TO ACT, WHEN TO WAIT: Modeling the Intent-Action Alignment Problem in Dialogue |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2506.01881 |