# Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent

arXiv: https://arxiv.org/abs/2609.38604 · HTML: https://mlsanity.com/paper/2609.38604/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 35 of its 80 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 35)

- [Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents](https://mlsanity.com/paper/2604.06132/) (2026)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications](https://mlsanity.com/paper/2509.26490/) (2025)
- [UserRL: Training Interactive User-Centric Agent via Reinforcement Learning](https://mlsanity.com/paper/2509.19736/) (2025)
- [HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?](https://mlsanity.com/paper/2604.09408/) (2026)
- [ChatShop: Interactive Information Seeking with Language Agents](https://mlsanity.com/paper/2404.09911/) (2024)
- [ClarQ-LLM: A Benchmark for Models Clarifying and Requesting Information in Task-Oriented Dialog](https://mlsanity.com/paper/2409.06097/) (2024)
- [From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents](https://mlsanity.com/paper/2601.22607/) (2026)
- [BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions](https://mlsanity.com/paper/2510.05318/) (2025)
- [Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents](https://mlsanity.com/paper/2602.16699/) (2026)
- [HorizonBench: Long-Horizon Personalization with Evolving Preferences](https://mlsanity.com/paper/2604.17283/) (2026)
- [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation](https://mlsanity.com/paper/2604.00892/) (2026)
- [InfoPO: Information-Driven Policy Optimization for User-Centric Agents](https://mlsanity.com/paper/2603.00656/) (2026)
- [SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions](https://mlsanity.com/paper/2606.30573/) (2026)
- [Flex-TravelPlanner: A Benchmark for Flexible Planning with Language Agents](https://mlsanity.com/paper/2506.04649/) (2025)
- [Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents](https://mlsanity.com/paper/2510.04491/) (2025)
- [TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios](https://mlsanity.com/paper/2602.01675/) (2026)
- [Coding Agents Are Guessing: Measuring Action-Boundary Violations in Underspecified DevOps Instructions](https://mlsanity.com/paper/2607.02294/) (2026)
- [LLMs Get Lost in Evolving User Intent](https://mlsanity.com/paper/2607.20734/) (2026)
- [Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction](https://mlsanity.com/paper/2602.02455/) (2026)
- [ClarEval: A Benchmark for Evaluating Clarification Skills of Code Agents under Ambiguous Instructions](https://mlsanity.com/paper/2603.00187/) (2026)
- [LHAW: Controllable Underspecification for Long-Horizon Tasks](https://mlsanity.com/paper/2602.10525/) (2026)
- [Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning](https://mlsanity.com/paper/2604.09813/) (2026)
- [One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL](https://mlsanity.com/paper/2608.12253/) (2026)
- [EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptions](https://mlsanity.com/paper/2604.16456/) (2026)
- [Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents](https://mlsanity.com/paper/2605.09698/) (2026)
- [DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration](https://mlsanity.com/paper/2606.03103/) (2026)
- [EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent](https://mlsanity.com/paper/2606.17698/) (2026)
- [CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship](https://mlsanity.com/paper/2608.02046/) (2026)
- [DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settings](https://mlsanity.com/paper/2606.22877/) (2026)

## Built on by (most cited first, 1 of 1)

- [CLEAT: Learning Value-Guided Clarification for Interactive Agents](https://mlsanity.com/paper/2610.12655/) (2026)

## Abstract (arXiv)

Modern LLM agents increasingly tackle complex tasks through interactive, long-horizon exchanges with users, while existing benchmarks generally assume that users always accurately and sufficiently communicate a fixed intent. However, this oracle communication assumption rarely holds in practice: users may miscommunicate, change their goals, and run out of patience. We define this task setting as Interactive Intent Alignment, where agents must recover and continuously track the user's current intent despite imperfect communication and evolving goals. To study this setting, we introduce Drift-Bench++, a principled benchmark construction pipeline for verified executable tasks with controlled misalignment and intent shifts, along with an interaction protocol featuring finite patience, diverse simulated users, and silent interaction-conditioned shifts. We further develop GRIP, a comprehensive evaluation protocol covering task grounding, user realism, inquiry effectiveness, and adaptation to evolving intent. Across diverse environments, models, and interaction conditions, stronger interaction consistently helps but remains far from oracle performance; Validation on deployed ProdAgent sessions further shows that the modeled failures are prevalent and consequential in deployment. By providing a unified, executable benchmark for interactive intent alignment, Drift-Bench++ offers a foundation for evaluating and advancing agents under realistic communication and evolving intent.