# LLMs Get Lost in Evolving User Intent

arXiv: https://arxiv.org/abs/2607.20734 · HTML: https://mlsanity.com/paper/2607.20734/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 21 of 21)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks](https://mlsanity.com/paper/2510.04374/) (2025)
- [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://mlsanity.com/paper/2503.15478/) (2025)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?](https://mlsanity.com/paper/2510.05444/) (2025)
- [Training Proactive and Personalized LLM Agents](https://mlsanity.com/paper/2511.02208/) (2025)
- [SWE-chat: Coding Agent Interactions From Real Users in the Wild](https://mlsanity.com/paper/2604.20779/) (2026)
- [On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots](https://mlsanity.com/paper/2406.01633/) (2024)
- [Learning Personalized Agents from Human Feedback](https://mlsanity.com/paper/2602.16173/) (2026)
- [TOM-SWE: User Mental Modeling For Software Engineering Agents](https://mlsanity.com/paper/2510.21903/) (2025)
- [OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability](https://mlsanity.com/paper/2511.20766/) (2025)
- [LLMs Corrupt Your Documents When You Delegate](https://mlsanity.com/paper/2604.15597/) (2026)
- [Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions](https://mlsanity.com/paper/2411.10163/) (2024)

## Built on by (most cited first, 10 of 10)

- [Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent](https://mlsanity.com/paper/2609.38604/) (2026)
- [Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale](https://mlsanity.com/paper/2609.30137/) (2026)
- [When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents](https://mlsanity.com/paper/2609.32520/) (2026)
- [Lost with a Map: Conversational State and Behavioral Reliability in Language Models](https://mlsanity.com/paper/2609.33883/) (2026)
- [Dataset Signatures in Human-LLM Interactions and User Modeling](https://mlsanity.com/paper/2610.05534/) (2026)
- [You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue](https://mlsanity.com/paper/2610.06496/) (2026)
- [Training User Simulators with Latent Intrinsic Feedback](https://mlsanity.com/paper/2610.13617/) (2026)
- [Where Did We Go Wrong? Localizing Errors to Repair Multi-Turn Conversations](https://mlsanity.com/paper/2610.15154/) (2026)
- [Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints](https://mlsanity.com/paper/2610.16155/) (2026)
- [Whose turn is it? Context-guided model routing for stateful agents](https://mlsanity.com/paper/2610.19292/) (2026)

## Abstract (arXiv)

As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet genuine interaction is inherently dynamic: users rarely specify their intent upfront, instead disclosing, revising, and reshaping it as the conversation unfolds. Despite this, LLMs are still predominantly evaluated or trained in single-turn, fully-specified settings, leaving open a fundamental question: how well do LLMs track and act on user intent as it evolves over the course of a conversation? To study this, we introduce a framework that transforms static, single-turn tasks into dynamic multi-turn conversations in which the user's intent evolves across turns--incrementally revealed, revised, and at times redirected mid-conversation--while preserving each task's original evaluation protocol, enabling existing benchmarks to be reused as controlled testbeds without new annotation. Across multiple tasks, we surface a consistent phenomenon: strong static-setting performance does not transfer to the evolving-intent setting, with substantial drops across model families. Our findings point to a fundamental gap: today's LLMs do not yet faithfully track and act on the user's evolving intent, a capability invisible to static evaluation yet critical for future collaborative agents.