cs.AIAug 16, 2026

Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents

Authors: Meiling Tao, Yiling Tao, Peng Wang

Organizations: University of Electronic Science and Technology of China · Shenzhen International Graduate School, Tsinghua University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

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.

Figures & tables

Figure 1: Overview of the IDSS framework. At each turn, the agent receives a user message or tool return: the fact layer converts tool returns into structured entities via deterministic parsing, while the state layer is updated by the agent during reasoning to reflect intents, variables, and constraints. New facts trigger cross-layer constraint propagation ( red arrows ), which may block infeasible intents and activate subsequent ones. Left: multi-turn dialogue timeline. Right: prompt assembly and LLM output. Blue arrows indicate tool returns parsed into the fact layer. Orange arrows indicate the updated state block being fed back into the next prompt.
ModelMethodτ\tau -benchVitaBench (Avg@4)UserBench
RetailAirlineDeliveryIn-storeOTACrossScoreCERPE (%)
Avg@4pass 4Avg@4pass 4
GPT-5.5ReAct77.546.063.528.552.061.534.022.50.3680.40528.5
StateAct78.247.064.229.552.562.035.523.50.3780.41429.0
ReSum52.028.548.522.044.552.030.225.50.3800.41829.8
IterResearch70.538.552.523.530.044.520.012.00.3850.42230.2
Table 1: Main results across three benchmarks with eight models. Bold indicates best, underline indicates second best within each model group. Row background reflects improvement over the ReAct baseline: deeper blue indicates larger gains, deeper red indicates larger degradation.
Figure 2: Normalized performance radar across seven evaluation dimensions. IDSS (red) achieves the largest coverage area.
Configurationτ\tau -bench Avg@4τ\tau -bench pass 4VitaBench Avg@4UserBench Score
Full IDSS67.034.842.20.382
w/o Fact Layer64.831.339.70.372
w/o State Layer65.532.339.40.350
w/o Constraint Modeling66.033.640.70.368
Vanilla63.930.037.10.330
Table 2: Ablation results of IDSS on GPT-4.1 across three benchmarks.
Figure 3: Trajectory outcomes and primary error types for IDSS and baselines.
Figure 4: Efficiency comparison of IDSS and baselines.
Figure 5: Case study on a τ\tau -bench Airline task. IDSS propagates a tool-grounded fare-class fact to block an infeasible modification path and activate a feasible alternative while preserving the user’s baggage requirement.
More in this topic

State Tracking

State tracking studies how AI systems maintain and update information about entities, tasks, or environments across sequential observations and actions.

See all 99 papers

Explore similar work

CardsList
Oct 24, 2026

IntentDelta: A Human-Constructed Benchmark for Evolving User Intent

Language-model agents must adapt as users revise their requirements and priorities during complex tasks. We introduce IntentDelta, a human-constructed multi-turn benchmark with 638 trajectories and 3,766 turns across WebShop and TravelPlanner. Each turn pairs a user utterance with a cumulative intention state and human reference actions. The trajectories are cross-verified and cover feasibility- and preference-driven changes in constraints and priorities. We evaluate eleven agents on intention recovery and action quality. Average Intention Recovery is 33.1% in TravelPlanner and 44.7% in WebShop, while average Action Score is 31.6% and 41.0%, respectively. Agents struggle to preserve earlier requirements and distinguish soft preferences from must-have constraints. Correct intention recovery also does not guarantee successful execution, highlighting challenges in translating evolving user intentions into actions.

Jieyu Zhou, Zijian Wang, Yun Wang

Georgia Institute of Technology, Atlanta, USA · Microsoft Research, Hong Kong SAR, China

LLM Agent EvaluationAI Agent BenchmarksLLM Agent Planning
AskPDF
Sep 26, 2026

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

LLM agents often operate over multi-turn interactions in which user intent changes before execution. We study intent drift: the failure mode in which superseded parts of the user's intent continue to influence the final answer or tool action. We introduce IntentFlux, an executable benchmark that converts verifiable tasks into dialogues with controlled intent changes while preserving their original graders. In a 627-case calibration, mean task score falls from 0.476 to 0.384 as dialogues contain more superseded and withdrawn information. Across eight models, the rate of fully correct solutions is significantly lower when the same final task must be recovered from an evolving dialogue rather than given directly in a single turn. We further introduce StateForge, which explicitly maintains the active requirements before generation. On General-Test, it improves mean task score from 0.367 to 0.467. Providing the ground-truth final state improves performance further but still does not recover single-turn performance, indicating that state-estimation errors explain only part of the gap. These results establish intent drift as a measurable multi-turn failure mode and explicit state maintenance as a partial mitigation.

Yanjie Zhang, Bowen Cao, Zixin Chen +1

HKUST, Hong Kong SAR, China · CUHK, Hong Kong SAR, China · LIGHTSPEED, Shenzhen, China

LLM AgentsLLM Agent EvaluationLLM Agent ReliabilityAI Agent Benchmarks
AskPDF
Jun 9, 2026

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution--properties absent from existing datasets. We propose ISE (Intent -> Simulate -> Execute), a three-stage synthesis paradigm that addresses these gaps jointly. Stage 1 constructs roughly 50000 structured intents via a 4D framework (Persona x Domain x Task x Complexity); after deduplication the pool contains 43956 unique intents and attains a Vendi Score of 61.57 over the entire pool on mpnet-base-v2 embeddings (cosine kernel, q=1). Stage 2 drives multi-turn user-agent interaction through a role-locked user simulator that grounds each user turn in actual execution outcomes, producing 23132 complete trajectories averaging 8.12 user turns and 68.24 total dialogue turns. Stage 3 runs every tool call inside a live, isolated OS workspace, generating authentic failure-recovery dynamics instead of simulated responses. Fine-tuning on ISETrace improves ClawEval pass@1 from 19.3 to 37.7 using Qwen3-8B on agent tool-use tasks with a standard protocol. This result outperforms zero-shot GPT-4o and the larger Qwen3-32B base model which is four times bigger. An ablation on Stage 2 proves multi-turn simulation brings a large portion of the performance gain. We release all source code and dataset at https://github.com/Valiere01/ISE-Trace.

Siyuan Luo, Nairong Zheng, Lin Zhou +6

University of Electronic Science and Technology of China · SenseTime Research

Synthetic Data GenerationTool-Using AgentsSynthetic Data Generation for LLM AgentsLLM Agent Trajectory SynthesisLLM Agent TrainingLong-Horizon LLM Agents
AskPDF