Skip to content

Lost with a Map: Conversational State and Behavioral Reliability in Language Models

Sep 2026 · arXiv.org · Vol abs/2609.33883 · 0 citations · 39 references
Computer Science

TL;DR

These findings motivate a state-action controller that starts from the base model action and selectively edits it using structural readouts, without requiring a complete predicted belief state as an intermediate representation.

Abstract

Task-oriented dialogue requires maintaining and updating information across turns, yet language models expose no explicit belief-state object. We study how conversational state is represented, updated, and used inside eight instruction-tuned language models from four families on MultiWOZ and SGD. Structure and values separate: which domains, slots, and requests are active is linearly readable just before the model acts, whereas exact values are far more readable where the user stated them. After a user changes a value, both values remain accessible at their mentions, and causal interventions show that both continue to influence the model's action. In natural closed-loop interaction, query failures separate into cases of weak structural support, incorrect value resolution, and failure to deploy otherwise-supported constraints, with targeted interventions producing systematically different repair behavior across these cases. These findings motivate a state-action controller that starts from the base model action and selectively edits it using structural readouts, without requiring a complete predicted belief state as an intermediate representation. On held-out MultiWOZ interaction across five models, it raises the base model exact-query accuracy from .318 to .621 and task success from .272 to .371 at negligible added cost. Overall, reliable interaction requires not only retaining conversational information, but resolving which available constraints currently apply and ensuring that they govern action.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue

When a large language model handles a multi-turn task and a user proposes a change but ultimately rejects it, the model should continue as if nothing changed. We find a surprising failure: merely mentioning a rejected change can derail task execution, even when the user's final intent remains unchanged. To systematical...

Junle Chen, Wei Chen, Zheng-Jun Huang et al. · 0 citations
#machine learning Preprint Sep 2026

How Do Language Models Choose Between Context and Memory?

The results suggest that authority computations may be task-dependent, rather than reusable across tasks, and suggest that authority computations may be task-dependent, rather than reusable across tasks.

Benjamin Shih, John Winnicki, Arianna Cao · 0 citations
#artificial intelligence Preprint Aug 2026

MIRAGE: How Conversation State Shapes Historical Evidence Use in Multimodal Personal Agents

Findings show that historical evidence use should be evaluated under state variation, rather than inferred from outcome-only correctness, and that open-weight models rely heavily on context continuity and are reluctant to spontaneously switch to tool-mediated retrieval when provenance fails.

Yu Liu, Wen-Xiao Zhang, Cheng Hu et al. · 0 citations

Clarification Is Not Correction: LLMs Fail to Let Go

Research for interactive LLMs from retaining more context toward preserving uncertainty is redirected from retaining more context toward preserving uncertainty, to motivate uncertainty-preserving state management.

Jian-Zhe Lin, Xiao-Lin Li, Fei Wang et al. · 0 citations

Language Models Act on Hidden Valence

It is demonstrated that valence-related activation patterns leave hidden traces that predictably govern later choices, even when all visible tokens are identical across conditions, and whether these traces are accompanied by any subjective experience relevant to model welfare remains unclear.

Cameron Berg, Caspar Kaiser · 2 citations · ⚡1

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.