Skip to content

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

Sep 2026 · 0 citations · 41 references
Computer Science

TL;DR

State-Grounded Conditioning is introduced, 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 the authors call direction drift: task-complete responses whose chosen direction misaligns with the current state.

Abstract

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.

View source

Similar papers

#artificial intelligence Preprint Aug 2026

SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents

SAGE (State-Grounded Abstention-Aware Evaluation), which compiles a workflow specification and per-turn state diff into atomic, schema-grounded criteria and routes each through a cascade of symbolic and encoder/NLI verifiers that abstain rather than guess, aggregating criterion verdicts into a turn-level decision with...

Rayan Khoury, Shih-Yao Lin, P. Mishra · 0 citations
Conference Aug 2026

CM-USR: Critical-Missing Calibrated User-State Regeneration for Lost-in-Conversation

Large language models (LLMs) often solve a fully specified instruction but fail when the same evidence arrives over multiple turns, a failure known as Lost-in-Conversation (LiC). We present CM-USR, a multi-agent inference-time systems that combines Critical-Missing (CM) calibration with User State and Regeneration (USR...

Ya-Qian Xu, Xiong Li · 0 citations

When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents

Intent drift is established as a measurable multi-turn failure mode and explicit state maintenance as a partial mitigation and IntentFlux is introduced, an executable benchmark that converts verifiable tasks into dialogues with controlled intent changes while preserving their original graders.

Yan-Jie Zhang, Bo-Wen Cao, Zi-Xin Chen et al. · 2 citations
#artificial intelligence Preprint Oct 2026

XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions

General turn-taking behavior in real-time dialogue systems requires deciding whether to keep listening or start responding while listening, and whether to continue or stop while speaking. Existing turn detectors use heterogeneous, task-specific label spaces and are often trained on limited annotations or evaluated on i...

Zhan-Xun Liu, Yi-Fan Duan, Heng-Tao Wu et al. · 0 citations

Related blog posts

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