# WHEN TO ACT, WHEN TO WAIT: Modeling the Intent-Action Alignment Problem in Dialogue

arXiv: https://arxiv.org/abs/2506.01881 · HTML: https://mlsanity.com/paper/2506.01881/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 8 of 8)

- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents](https://mlsanity.com/paper/2201.04723/) (2022)
- [Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward](https://mlsanity.com/paper/2504.03206/) (2025)
- [Socio-Culturally Aware Evaluation Framework for LLM-Based Content Moderation](https://mlsanity.com/paper/2412.13578/) (2024)
- [Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems](https://mlsanity.com/paper/2005.13119/) (2020)

## Abstract (arXiv)

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.