Metraipolis › archive › dc_fd1d38651fae

State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State — arXiv:2609.27606

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27606
License (as archived)
CC0-1.0
Archived
2026-10-08T09:11:26.500Z
SHA-256 of the archived text
de0346ab843e90f0219204dea7411431839a80194e3af31a321d670bdbca3334
Stable URL of this page
https://metraipolis.com/documento/dc_fd1d38651fae

How to cite

State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State — arXiv:2609.27606 — arXiv (en), https://arxiv.org/abs/2609.27606 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd1d38651fae (Metraipolis archive dc_fd1d38651fae, sha256 de0346ab843e90f0219204dea7411431839a80194e3af31a321d670bdbca3334)
BibTeX
@misc{dcfd1d38651fae,
  title = {State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State — arXiv:2609.27606},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27606},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd1d38651fae; sha256 de0346ab843e90f0219204dea7411431839a80194e3af31a321d670bdbca3334},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27606. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents that must condition on live user state (game state, session history, live inventory), and a distinct failure class we call direction drift: task-complete responses whose chosen direction misaligns with the current state. SGC externalises state-dependent control into rule kernels over structured inputs and three primary state slices, via Perception, Grounding, and Interaction wrappers with explicit conditioning dependencies. We evaluate SGC on a 200-session anonymised benchmark ($\approx$1,000 assistant model turns) from an in-game conversational coaching agent that guides players through consecutive competitive matches, reporting mean first-token latency and five human-annotated dialogue-quality metrics that jointly cover factual grounding and coach-like guidance progression. The Perception wrapper holds mean first-token latency at 1.5s (vs. 6.1s for PE-Agent inside a production tool-use harness); enabling all three wrappers lifts turn-level grounded accuracy from 61.1%/69.8% (Prompting / PE-Agent) to 96.7% and session-level grounded accuracy from 20.0%/26.5% to 83.5%; session-level grounding-failure incidents drop by $\approx$78% relative to the strongest baseline. A cumulative ablation shows complementary incremental gains as the wrappers are added. These results inform approximate state-slice orthogonality, without establishing independent per-wrapper effects.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.27606 — 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 2026-10-08T08:13:26.518Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).