Interactive Task Alignment as a POMDP

• URL: http://arxiv.org/abs/2607.16412v1
• Date: Fri, 17 Jul 2026 18:04:38 GMT
• Title: Interactive Task Alignment as a POMDP
• Abstract summary: We introduce a general framework for converting specified tasks into underspecified interactions.<n>We validate our user simulator post hoc with a human user study.<n>We show that post-training with supervised fine-tuning and reinforcement learning improves task alignment, but models still lag behind humans in resolving uncertainty through interaction.
• Score: 17.743513722485876
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current benchmarks for language models primarily evaluate execution on fully specified tasks. However, real user tasks are often ambiguous. Users arrive with incomplete, exploratory, or even inconsistent goals, requiring the assistant to first determine the intended task before carrying it out. We study this problem as task alignment: the ability to align with a user on their intended task. We introduce a general framework for converting specified tasks into underspecified interactions, formalized as a POMDP in which the model must infer a latent task from partial and evolving user intent. We validate our user simulator post hoc with a human user study. Across shopping, coding, and professional work settings, we find that while models often perform well once the task is specified, models still struggle with task alignment: current models act prematurely, interact ineffectively, and fail to resolve ambiguous requests. Models on average recover the user's intended task only 22-32% of the time under ambiguity. In a human study in the same setting, humans reach 48%, outperforming all evaluated models. We show that post-training with supervised fine-tuning and reinforcement learning improves task alignment, but models still lag behind humans in resolving uncertainty through interaction. Together, our results suggest that current models still lack key interaction abilities required for reliable agency.

Related papers

• xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems [57.62172039072062]
  We introduce xDailyBench, a benchmark of 248 carefully curated tasks spanning 51 scenarios across personal life, white-collar work, learning and research, and cross-domain activities.<n>The tasks are grounded in requests that users have actually completed or genuinely intended to accomplish with AI, and are evaluated with fine-grained binary rubrics covering both explicit and implicit requirements.<n>The best models achieve a task-level score of 75.6%, while all models perform substantially worse on implicit than explicit requirements, with gaps no less than 9 percentage points.
  arXiv  Detail & Related papers  (2026-09-07T17:30:58Z)
• VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions [63.13827503828231]
  We introduce VitaBench 2.0, a benchmark for evaluating personalized and proactive agent behavior in long-term user interactions.<n>Results show that real-world personalization remains highly challenging even for state-of-the-art models.
  arXiv  Detail & Related papers  (2026-05-26T15:07:38Z)
• Modeling Distinct Human Interaction in Web Agents [59.600507469754575]
  We introduce the task of modeling human intervention to support collaborative web task execution.<n>We identify four distinct patterns of user interaction with agents -- hands-off supervision, hands-on oversight, collaborative task-solving, and full user takeover.<n>We deploy these intervention-aware models in live web navigation agents and evaluate them in a user study, finding a 26.5% increase in user-rated agent usefulness.
  arXiv  Detail & Related papers  (2026-02-19T18:11:28Z)
• BRIDGE: Predicting Human Task Completion Time From Model Performance [36.36759710005444]
  Existing approaches that rely on direct human task completion time annotations are costly, noisy, and difficult to scale across benchmarks.<n>We propose BRIDGE, a unified psychometric framework that learns the latent difficulty scale from model responses and anchors it to human task completion time.
  arXiv  Detail & Related papers  (2026-02-06T23:36:11Z)
• SureMap: Simultaneous Mean Estimation for Single-Task and Multi-Task Disaggregated Evaluation [75.56845750400116]
  Disaggregated evaluation -- estimation of performance of a machine learning model on different subpopulations -- is a core task when assessing performance and group-fairness of AI systems. We develop SureMap that has high estimation accuracy for both multi-task and single-task disaggregated evaluations of blackbox models. Our method combines maximum a posteriori (MAP) estimation using a well-chosen prior together with cross-validation-free tuning via Stein's unbiased risk estimate (SURE)
  arXiv  Detail & Related papers  (2024-11-14T17:53:35Z)
• MUSCLE: A Model Update Strategy for Compatible LLM Evolution [29.032461144831053]
  Large Language Models (LLMs) are regularly updated to enhance performance. Instance-level degradation (instance regression) of performance from one model version to the next can interfere with a user's mental model of the capabilities of a particular language model. We propose a training strategy to minimize the extent of instance regression in model updates.
  arXiv  Detail & Related papers  (2024-07-12T17:12:48Z)
• Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation [20.266695694005943]
  Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments. Data augmentation can increase robustness by making the model invariant to task-irrelevant changes in the agent's observation. We propose an interactive framework to leverage feedback directly from the user to identify personalized task-irrelevant concepts.
  arXiv  Detail & Related papers  (2023-07-12T17:55:08Z)
• Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models [80.23791222509644]
  Inconsistent AI models are considered brittle and untrustworthy by human users. We find that state-of-the-art vision-language models suffer from a surprisingly high degree of inconsistent behavior across tasks. We propose a rank correlation-based auxiliary training objective, computed over large automatically created cross-task contrast sets.
  arXiv  Detail & Related papers  (2023-03-28T16:57:12Z)
• Task Ambiguity in Humans and Language Models [7.033374427612259]
  We propose AmbiBench, a new benchmark of ambiguously-specified classification tasks. We evaluate humans and models on AmbiBench by seeing how well they identify the intended task. We show how to dramatically improve the accuracy of language models trained without large-scale human feedback training.
  arXiv  Detail & Related papers  (2022-12-20T18:35:33Z)
• Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks [86.66733026149892]
  We propose Uni-Perceiver v2, which is the first generalist model capable of handling major large-scale vision and vision-gnostic tasks. Specifically, images are encoded as general region proposals, while texts are encoded via a Transformer-based language model. Uni-Perceiver v2 achieves competitive performance on a broad range of vision and vision-language tasks.
  arXiv  Detail & Related papers  (2022-11-17T18:59:52Z)
• Meta-Regularization by Enforcing Mutual-Exclusiveness [0.8057006406834467]
  We propose a regularization technique for meta-learning models that gives the model designer more control over the information flow during meta-training. Our proposed regularization function shows an accuracy boost of $sim$ $36%$ on the Omniglot dataset.
  arXiv  Detail & Related papers  (2021-01-24T22:57:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.