From Feasibility to Desirability: Plan, Learn, Adapt (PLA) Framework for Personalized On-Device Itinerary Generation

• URL: http://arxiv.org/abs/2607.15552v1
• Date: Fri, 17 Jul 2026 01:52:02 GMT
• Title: From Feasibility to Desirability: Plan, Learn, Adapt (PLA) Framework for Personalized On-Device Itinerary Generation
• Abstract summary: Plan, Learn, Adapt is a three-stage framework for personalized on-device itinerary generation.<n>On 2,519 pairwise human comparisons across more than 100 U.S. cities, PLA achieves a 67.8% win rate, 11.2 percentage points above the best single planner, with 100% feasibility.<n>In production deployment within FlyEnJoy, PLA increased itinerary completion rates by 91%, with 109.9 ms average on-device latency.
• Score: 1.6391892978433935
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating personalized trip itineraries is a complex planning task and involves a tension between hard combinatorial feasibility and soft latent desirability. Classical optimization enforces constraints but fails to capture subjective traveler preferences. While learning-based approaches model preferences, they cannot guarantee feasibility. Mobile deployment imposes additional resource constraints on both. To address this, we propose Plan, Learn, Adapt (PLA), a three-stage framework for personalized on-device itinerary generation. The Plan stage builds a heterogeneous ensemble of lightweight planners that produces structurally diverse feasible candidates. From pairwise itinerary comparisons, Learn fits a compact Bradley-Terry reward model that captures emergent schedule properties such as pacing, geographic coherence, and day balance, which per-POI signals miss. Finally, Adapt applies feasibility-preserving local refinement within a device-aware compute budget; every intermediate state is feasible by construction. On 2,519 pairwise human comparisons across more than 100 U.S. cities, the reward-guided ensemble achieves a 67.8% win rate, 11.2 percentage points above the best single planner, with 100% feasibility. Three frontier LLMs, GPT-5, Claude Opus 4.5, and Gemini 3 Pro, achieve 0% feasibility under the same constraints. The reward model generalizes across held-out cities, with a 67.6% mean leave-one-city-out accuracy. In production deployment within FlyEnJoy, PLA increased itinerary completion rates by 91%, with 109.9 ms average on-device latency.

Related papers

• LePlanner: An Iterative Amortized Controller For World Models [0.0]
  We propose LePlanner, an amortized iterative controller that learns to construct and refine latent action sequences through a frozen world-model predictor.<n>LePlanner is trained with an arrival-and-hold objective that encourages the controller to reach the goal at the earliest feasible horizon and remain there.<n>It achieves success rates of 98% on PushT, 100% on Reacher, 100% on TwoRooms, and 92% on the OGBench Cube task.
  arXiv  Detail & Related papers  (2026-09-12T10:01:21Z)
• Robust Asynchronous Planning via Auto-Formalization [18.999996458563373]
  LLMs can plan by either generating action sequences directly as a Planner or translating tasks into domain specific language for an external solver as a Formalizer.<n>We unify these challenges that under a single formulation and introduce the first three benchmarks that address each at scale.<n>We conclude the choice of formal representation primarily determines whether planning scales.
  arXiv  Detail & Related papers  (2026-05-31T03:28:42Z)
• Mosaic: An Extensible Framework for Composing Rule-Based and Learned Motion Planners [5.399177691034965]
  Rule-based planners offer predictable and explainable behavior; learned planners exhibit strong adaptability but suffer from reduced transparency and occasional safety violations.<n>We introduce Mosaic, a framework for structured decision-making that integrates both paradigms through arbitration graphs.<n>In experimental evaluation, Mosaic achieves 95.48 CLS-NR and 93.98 CLS-R on the Val14 closed-loop benchmark, setting a new state of the art, while reducing at-fault collisions by 30% compared to either planner in isolation.
  arXiv  Detail & Related papers  (2026-04-15T13:23:47Z)
• HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel [17.262462566213244]
  We propose HiMAP-Travel, a hierarchical multi-agent framework that splits planning into strategic coordination and parallel day-level execution.<n>On TravelPlanner, HiMAP-Travel with Qwen3-8B achieves 52.78% validation and 52.65% test Final Pass Rate (FPR)
  arXiv  Detail & Related papers  (2026-03-05T02:55:53Z)
• MagicAgent: Towards Generalized Agent Planning [73.21129030631421]
  We present textbfMagicAgent, a series of foundation models specifically designed for generalized agent planning.<n>We introduce a lightweight and scalable synthetic data framework that generates high-quality trajectories across diverse planning tasks.<n>We show that MagicAgent-32B and MagicAgent-30B-A3B achieve superior performance across diverse open-source benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T01:39:16Z)
• TriFlow: A Progressive Multi-Agent Framework for Intelligent Trip Planning [2.374752841069747]
  Real-world trip planning requires transforming open-ended user requests into executable itineraries under strict spatial, temporal, and budgetary constraints.<n>Existing LLM-based agents struggle with constraint satisfaction, tool coordination, and efficiency.<n>We present TriFlow, a progressive multi-agent framework that unifies structured reasoning and language-based flexibility.
  arXiv  Detail & Related papers  (2025-12-12T04:27:22Z)
• TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel Planning [7.841787597078323]
  TripCraft establishes a new benchmark for LLM driven personalized travel planning, offering a more realistic, constraint aware framework for itinerary generation.<n>Our parameter informed setting significantly enhances meal scheduling, improving the Temporal Meal Score from 61% to 80% in a 7 day scenario.
  arXiv  Detail & Related papers  (2025-02-27T20:33:28Z)
• Reconsidering utility: unveiling the limitations of synthetic mobility data generation algorithms in real-life scenarios [49.1574468325115]
  We evaluate the utility of five state-of-the-art synthesis approaches in terms of real-world applicability. We focus on so-called trip data that encode fine granular urban movements such as GPS-tracked taxi rides. One model fails to produce data within reasonable time and another generates too many jumps to meet the requirements for map matching.
  arXiv  Detail & Related papers  (2024-07-03T16:08:05Z)
• NATURAL PLAN: Benchmarking LLMs on Natural Language Planning [109.73382347588417]
  We introduce NATURAL PLAN, a realistic planning benchmark in natural language containing 3 key tasks: Trip Planning, Meeting Planning, and Calendar Scheduling. We focus our evaluation on the planning capabilities of LLMs with full information on the task, by providing outputs from tools such as Google Flights, Google Maps, and Google Calendar as contexts to the models.
  arXiv  Detail & Related papers  (2024-06-06T21:27:35Z)
• PDDLEGO: Iterative Planning in Textual Environments [56.12148805913657]
  Planning in textual environments has been shown to be a long-standing challenge even for current models. We propose PDDLEGO that iteratively construct a planning representation that can lead to a partial plan for a given sub-goal. We show that plans produced by few-shot PDDLEGO are 43% more efficient than generating plans end-to-end on the Coin Collector simulation.
  arXiv  Detail & Related papers  (2024-05-30T08:01:20Z)
• LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning [65.86754998249224]
  We develop a novel hybrid planner that leverages a conventional rule-based planner in conjunction with an LLM-based planner. Our approach navigates complex scenarios which existing planners struggle with, produces well-reasoned outputs while also remaining grounded through working alongside the rule-based approach.
  arXiv  Detail & Related papers  (2023-12-30T02:53:45Z)
• Differentiable Spatial Planning using Transformers [87.90709874369192]
  We propose Spatial Planning Transformers (SPT), which given an obstacle map learns to generate actions by planning over long-range spatial dependencies. In the setting where the ground truth map is not known to the agent, we leverage pre-trained SPTs in an end-to-end framework. SPTs outperform prior state-of-the-art differentiable planners across all the setups for both manipulation and navigation tasks.
  arXiv  Detail & Related papers  (2021-12-02T06:48:16Z)

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.