Metraipolis › archive › dc_7ddca0fd8182

Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents — arXiv:2608.15755

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15755
License (as archived)
CC0-1.0
Archived
2026-10-18T17:26:14.188Z
SHA-256 of the archived text
1d52896a0613483230cd00f575bb3c4bdf3813b66278b8ae397daec8efa69b60
Stable URL of this page
https://metraipolis.com/documento/dc_7ddca0fd8182

How to cite

Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents — arXiv:2608.15755 — arXiv (en), https://arxiv.org/abs/2608.15755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ddca0fd8182 (Metraipolis archive dc_7ddca0fd8182, sha256 1d52896a0613483230cd00f575bb3c4bdf3813b66278b8ae397daec8efa69b60)
BibTeX
@misc{dc7ddca0fd8182,
  title = {Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents — arXiv:2608.15755},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15755},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ddca0fd8182; sha256 1d52896a0613483230cd00f575bb3c4bdf3813b66278b8ae397daec8efa69b60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

User-centric multi-turn agents must act on an evolving task situation shaped by changing user intents, accumulated tool-grounded facts, missing information, and execution constraints. Existing context-management methods improve the use of past interaction history, but rarely maintain an explicit situation state that separates grounded facts from task-state judgments. As a result, agents often need to infer fine-grained attributes, task dependencies, and constraint satisfaction implicitly from dialogue traces. We propose Intent-Driven Situation States (IDSS), a training-free framework that maintains an explicit situation state alongside the dialogue. IDSS parses tool returns into provenance-aware entities and attributes, tracks user intents, required variables, constraints, and execution status, and propagates new facts to task constraints to update action executability. This allows agents to avoid infeasible actions, advance dependent goals, and reuse relevant information without repeatedly searching raw history. Experiments on three interactive benchmarks across eight LLMs show that IDSS improves task completion, preference elicitation, and interaction efficiency, with clear gains on tasks involving multi-entity coordination, evolving user constraints, and constraint-aware replanning. Ablations and error analyses show that these improvements come from the interaction between fact persistence, intent-centered state tracking, and constraint modeling. These results suggest that explicit situation tracking offers an effective alternative to history-centric context management for reliable user-centric multi-turn agents.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15755 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.828Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).