This work traces the dynamics of constraints and preferences as they are surfaced, refined, and coordinated throughout the planning process, and identified 11 actions revolving around constraints and preferences, which shaped the planning process.
Abstract
Planning is a common yet complex activity shaped by constraints to satisfy and preferences to balance. Travel planning, as both an everyday activity and a frequent benchmark for evaluating intelligent systems, offers a rich context for examining how constraints and preferences emerge and evolve. While recent AI systems have achieved impressive results in generating personalized itineraries, they often assume that users can articulate stable goals upfront. To understand how real-world planning unfolds, we conducted a two-part interview study: one with eight travelers reflecting on their planning experiences, and one with nine travel agents sharing professional practices. We trace the dynamics of constraints and preferences as they are surfaced, refined, and coordinated throughout the planning process, and identified 11 actions revolving around constraints and preferences, which shaped the planning process. We offer design heuristics for planning tools that better support human-AI collaborative actions to support the fluid, contingent nature of planning.
This work proposes TRIPPULSE1, a multi- agent framework for review-grounded travel planning, and introduces Review-Grounded Per- sona Alignment (RGPA), an LLM-as-a-Judge metric for evaluating alignment with human- centric travel experiences.
This work introduces AcCoRD, a user-agent collaboration benchmark requiring agents to handle diverse user preference dynamics in two domains: online shopping and travel planning, and evaluates five frontier LLMs under two prompting strategies: vanilla ReAct, and an uncertainty-guided variant that prompts models to iden...
A new task, Behavior-Aware Travel Planning, which infers user preferences directly from past behaviors and generates personalized travel plans and proposes B2T-Agent, a reinforcement learning-based agent that leverages user behavior trajectories, interacts with external tools for preference-aligned retrieval, and maint...
Zihao Cheng, Yingyu Shan, Hongru Wang et al.· 1 citation
Recent AI alignment work often frames alignment as a pre-deployment optimization problem: collect human feedback, learn preferences or principles, finetune the model, and deploy an aligned system. This framing has produced major progress, but it under-specifies what happens once AI systems act as agents on users'behalf...
Actual, realistic domains are characterised by inherent uncertainty, compelling the development of planning strategies that enable the embracing of risks, where performing actions incurs costs, such as fuel and time, that cannot be predefined as constants during planning. In such domains, an agent’s perspective of desi...
Planning is increasingly important for long-horizon agents, where successful execution requires coordinating subgoals, tool use, and intermediate outcomes over many steps. Yet assumptions made during planning may be invalidated by the environment, tools may return unexpected results, or actions may fail. Effective agen...
Syamantak Kumar, Jiang Guo, Hassan Hamad et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 18, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.