pith. sign in

arxiv: 2605.14628 · v1 · pith:KYD54PRMnew · submitted 2026-05-14 · 💻 cs.HC

SmartWalkCoach: An AI Companion for End-to-End Walking Guidance, Motivation, and Reflection

Xianzhe Zhang , Mingxuan Hu , Bufan Xue , Erick Purwanto , Thomas J Selig , Daniel Yonto This is my paper

Pith reviewed 2026-06-30 20:35 UTC · model grok-4.3

classification 💻 cs.HC
keywords AI companionwalking guidancemotivational dialogueuser experiencemobile healthagent architecturecontext-aware interventioncrossover study
0
0 comments X

The pith

An AI walking companion with motivational dialogue raises positive feelings and user experience ratings compared to information alone.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper sets out to demonstrate that a mobile AI system can handle the full cycle of walking—from conversational route planning to real-time guidance and post-walk reflection—while showing that adding relational, motivational prompts to factual information produces measurable gains in how people feel during the activity. A reader would care because everyday walking often lacks sustained engagement, and tools that combine practical help with encouragement could make the habit more appealing without requiring extra effort from the user. The central test is a field study that isolates the effect of the motivational layer through a controlled comparison of two versions of the same system.

Core claim

SmartWalkCoach coordinates three agents to manage route selection from nearby points of interest, deliver context-aware prompts that mix facts with encouragement, and generate concise post-walk summaries. In an in-the-wild AB/BA crossover trial with twelve participants, the version that included companion-like motivational dialogue produced significantly higher positive affect and better user-experience scores than the information-only version, with no detectable carryover between the two walks. Thematic analysis further identified that supportive relational phrasing and careful timing around fatigue or high-load moments are necessary for the motivational component to work.

What carries the argument

The AccompanyAgent, which generates just-in-time prompts that combine route information with relational encouragement at moments chosen to avoid high cognitive or physical load.

If this is right

  • Adding motivational dialogue alongside factual guidance increases reported positive feelings during walks.
  • Users rate the overall experience higher when the system uses companion-like relational language.
  • Interventions must be timed to avoid high-load moments such as steep sections or decision points.
  • Supportive phrasing and milestone-based encouragement form two core requirements for effective mobile walking companions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same motivational timing rules could apply to other repetitive outdoor activities where people need both directions and persistence support.
  • Voice-only versions might further lower the barrier to use by removing the need to look at a screen while moving.
  • Longer-term deployment could test whether the affect gains translate into higher walking frequency over weeks rather than single outings.

Load-bearing premise

The crossover design with twelve participants is large enough and free enough of order or fatigue effects for the linear mixed models to attribute outcome differences specifically to the presence of motivational dialogue.

What would settle it

A larger study repeating the same two conditions and finding no reliable difference in positive-feeling scores or user-experience ratings between information-only and information-plus-motivation walks would show the reported effect does not generalize.

Figures

Figures reproduced from arXiv: 2605.14628 by Bufan Xue, Daniel Yonto, Erick Purwanto, Mingxuan Hu, Thomas J Selig, Xianzhe Zhang.

Figure 1
Figure 1. Figure 1: Screenshots of the interaction in the pre-walk route [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Screenshots of an interaction between the user and [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
read the original abstract

We present SmartWalkCoach, a mobile AI companion that supports the full walking journey: from pre-walk planning to in-walk guidance through to post-walk reflection. Addressing a gap between map navigation and motivational coaching, SmartWalkCoach orchestrates three lightweight agents: (1) GeographyAgent for conversational route curation from nearby points of interest and user preferences while delegating pathfinding to map APIs; (2) AccompanyAgent for context-aware, just-in-time prompts that blend informational cues with relational encouragement; and (3) SummaryAgent for concise reflection and next-step planning. This end-to-end, tool-using design aims to lower cognitive load in planning and sustain engagement and motivation during walking through delivering dynamic, cadence-aware interventions. We conducted an in-the-wild, two-period AB/BA crossover study (N=12), where each participant completed two comparable walks with counterbalanced conditions: Information-only versus Information+Motivation. Linear mixed models show that adding motivational, companion-like dialogue significantly improved outcomes: participants reported higher positive feelings and better user experience, with no evidence of carryover. Thematic analysis surfaced two design imperatives for mobile companions: supportive, relational expression and context-aware timing (e.g., avoiding high-load moments, intervening at fatigue/milestones). Our contributions are: (i) an end-to-end, tool-using agent architecture for everyday walking that reduces cognitive load during planning and accompaniment; (ii) a controlled field evaluation linking context-aware motivation to affect and UX gains; and (iii) actionable design guidance on expression, timing, and frequency for mHealth companions.We outline limitations and paths toward multimodal, voice-first companions, with adaptive personalization mechanisms.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper presents SmartWalkCoach, a mobile AI system orchestrating three lightweight agents (GeographyAgent for route planning, AccompanyAgent for context-aware motivational prompts, and SummaryAgent for reflection) to support the full walking journey. It evaluates the system in an in-the-wild AB/BA crossover study (N=12) comparing Information-only vs. Information+Motivation conditions, reporting via linear mixed models that adding companion-like motivational dialogue yields significantly higher positive affect and user experience with no detected carryover, supplemented by thematic analysis yielding design guidelines on relational expression and context-aware timing.

Significance. If the statistical claims hold after addressing power and effect-size reporting, the work would provide a concrete end-to-end agent architecture for everyday mHealth accompaniment and empirical support for the value of relational, just-in-time motivation in reducing cognitive load and sustaining engagement during walking, together with actionable design imperatives that could inform future voice-first or adaptive companions.

major comments (2)
  1. [Abstract and Results] Abstract and Results (LMM analysis): The central claim that motivational dialogue produced significantly higher positive feelings and UX rests on linear mixed models from the N=12 crossover, yet the manuscript reports neither effect sizes, confidence intervals, nor a power analysis; with this sample size the absence of these quantities leaves the attribution of effects to the motivational component vulnerable to low power or undetected period/fatigue confounds.
  2. [Evaluation] Evaluation section (crossover design): The AB/BA design is counterbalanced and reports no carryover, but the manuscript does not describe sensitivity checks for order effects or between-subject variability in the LMM; given N=12, even modest undetected confounds could alter interpretation of the within-subject differences.
minor comments (2)
  1. [Abstract] The abstract states that exact p-values and error bars are omitted; adding these (or directing readers to a supplementary table) would improve transparency without altering the core narrative.
  2. [Thematic Analysis] Thematic analysis is described at a high level; specifying the coding scheme, inter-rater reliability, and how themes were derived from the 12 transcripts would strengthen the qualitative contribution.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments on the statistical reporting and evaluation design. We address each major comment below and will revise the manuscript accordingly to improve transparency.

read point-by-point responses

  1. Referee: [Abstract and Results] Abstract and Results (LMM analysis): The central claim that motivational dialogue produced significantly higher positive feelings and UX rests on linear mixed models from the N=12 crossover, yet the manuscript reports neither effect sizes, confidence intervals, nor a power analysis; with this sample size the absence of these quantities leaves the attribution of effects to the motivational component vulnerable to low power or undetected period/fatigue confounds.

    Authors: We agree that effect sizes, confidence intervals, and a power discussion are important for interpreting the LMM results with N=12. In the revised manuscript we will add Cohen's d (or equivalent) effect sizes and 95% confidence intervals for the significant effects on positive affect and UX. We will also include a brief post-hoc power note and explicitly acknowledge the exploratory nature of the study and the risk of low power or undetected confounds. These changes will be reflected in the Abstract, Results, and Discussion sections. revision: yes

  2. Referee: [Evaluation] Evaluation section (crossover design): The AB/BA design is counterbalanced and reports no carryover, but the manuscript does not describe sensitivity checks for order effects or between-subject variability in the LMM; given N=12, even modest undetected confounds could alter interpretation of the within-subject differences.

    Authors: We will expand the Evaluation section to describe sensitivity checks. This will include testing for period-by-condition interactions in the LMM to assess order effects, reporting variance components for between-subject variability, and confirming the absence of carryover. These details will demonstrate the robustness of the within-subject comparisons. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical claims rest on user-study data and LMM analysis

full rationale

The paper presents a system architecture and evaluates it via an in-the-wild AB/BA crossover study (N=12) with linear mixed models and thematic analysis. No equations, fitted parameters, predictions, or self-citations appear in the load-bearing claims. Results are reported directly from the described participant data and coding; the derivation chain contains no self-definitional, fitted-input, or self-citation reductions.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is an empirical HCI prototype paper with no mathematical model, fitted parameters, or background axioms invoked; the three agents are software design choices rather than postulated scientific entities.

pith-pipeline@v0.9.1-grok · 5854 in / 1106 out tokens · 28005 ms · 2026-06-30T20:35:51.799336+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

108 extracted references · 71 canonical work pages

  1. [1]

    Adnan Abbas, Caleb Wohn, Donghan Hu, Eugenia H Rho, and Sang Won Lee

  2. [2]

    InProceedings of the 7th ACM Conference on Conversational User Interfaces (CUI ’25)

    PITCH: Designing Agentic Conversational Support for Planning and Self-reflection. InProceedings of the 7th ACM Conference on Conversational User Interfaces (CUI ’25). Association for Computing Machinery, New York, NY, USA, Article 62, 22 pages. doi:10.1145/3719160.3736634

    work page doi:10.1145/3719160.3736634

  3. [3]

    Agarwal, Kimberly J

    Anish K. Agarwal, Kimberly J. Waddell, Dylan S. Small, Chalanda Evans, Tory O. Harrington, Rachel Djaraher, Ai Leen Oon, and Mitesh S. Patel. 2021. Effect of Gamification With and Without Financial Incentives to Increase Physical Activity Among Veterans Classified as Having Obesity or Overweight: A Ran- domized Clinical Trial.JAMA Network Open4, 7 (July 2...

    work page doi:10.1001/jamanetworkopen.2021.16256 2021

  4. [4]

    Valkiria Amaya, Matthias Chardon, Helen Klein, Thibauld Moulaert, and Nicolas Vuillerme. 2022. What Do We Know about the Use of the Walk-along Method to Identify the Perceived Neighborhood Environment Correlates of Walking Activity in Healthy Older Adults: Methodological Considerations Related to Data Collection—A Systematic Review.Sustainability14, 18 (2...

    work page doi:10.3390/su141811792 2022

  5. [5]

    Nathalie André, Marine Grousset, and Michel Audiffren. 2024. A Behavioral Perspective for Improving Exercise Adherence.Sports Medicine - Open10, 1 (May 2024), 56. doi:10.1186/s40798-024-00714-8

    work page doi:10.1186/s40798-024-00714-8 2024

  6. [6]

    Bokolo Anthony Jnr. 2025. User-centered AI-based voice-assistants for safe mobility of older people in urban context.AI & Society40, 2 (Feb. 2025), 545–568. doi:10.1007/s00146-024-01865-8

    work page doi:10.1007/s00146-024-01865-8 2025

  7. [7]

    Ryan R. Bailey. 2019. Goal Setting and Action Planning for Health Behavior Change.American Journal of Preventive Medicine13, 6 (2019), 615–618. doi:10. 1177/1559827617729634

    2019

  8. [8]

    Douglas Bates, Martin Mächler, Ben Bolker, and Steve Walker. 2015. Fitting Linear Mixed-Effects Models Using lme4.Journal of Statistical Software67, 1 (2015), 1–48. doi:10.18637/jss.v067.i01

    work page doi:10.18637/jss.v067.i01 2015

  9. [9]

    Pratool Bharti, Debraj De, Sriram Chellappan, and Sajal K Das. 2018. HuMAn: Complex activity recognition with multi-modal multi-positional body sensing. IEEE Transactions on Mobile Computing18, 4 (2018), 857–870

    2018

  10. [10]

    Bickmore and Rosalind W

    Timothy W. Bickmore and Rosalind W. Picard. 2005. Establishing and main- taining long-term human-computer relationships.ACM Trans. Comput.-Hum. Interact.12, 2 (June 2005), 293–327. doi:10.1145/1067860.1067867

    work page doi:10.1145/1067860.1067867 2005

  11. [11]

    Bickmore, Daniel Schulman, and Candace Sidner

    Timothy W. Bickmore, Daniel Schulman, and Candace Sidner. 2011. A reusable framework for health counseling dialogue systems based on a behavioral medicine ontology.Journal of Biomedical Informatics44, 2 (2011), 183–197. doi:10.1016/j.jbi.2010.12.006

    work page doi:10.1016/j.jbi.2010.12.006 2011

  12. [12]

    Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psy- chology.Qualitative Research in Psychology3, 2 (2006), 77–101. doi:10.1191/ 1478088706qp063oa

    2006

  13. [13]

    Annina Brügger, Kai-Florian Richter, and Sara Irina Fabrikant. 2019. How does navigation system behavior influence human behavior?Cognitive Research: SmartWalkCoach: An AI Companion for End-to-End Walking Guidance, Motivation, and Reflection IUI ’26, March 23–26, 2026, Paphos, Cyprus Principles and Implications4, 1 (Feb. 2019), 5. doi:10.1186/s41235-019-0156-5

    work page doi:10.1186/s41235-019-0156-5 2019

  14. [14]

    Anastasi

    Bernadette Capili and Joyce K. Anastasi. 2024. An Introduction to the Crossover Trial Design.The American Journal of Nursing124, 9 (Sept. 2024), 40–43. doi:10. 1097/01.NAJ.0001050812.23977.85

    arXiv 2024

  15. [15]

    Cummings

    Wanyi Chen, Meng-Wen Su, Nafisa Mehjabin, and Mary L. Cummings. 2024. Can LLMs plan paths in the real world? arXiv:2411.17912 [cs.AI] doi:10.48550/ arXiv.2411.17912

    arXiv 2024

  16. [16]

    Shankar, Kathryn M

    Yu-Peng Chen, Julia Woodward, Dinank Bista, Xuanpu Zhang, Ishvina Singh, Oluwatomisin Obajemu, Meena N. Shankar, Kathryn M. Ross, Jaime Ruiz, and Lisa Anthony. 2024. Investigating Contextual Notifications to Drive Self- Monitoring in mHealth Apps for Weight Maintenance. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolul...

    work page doi:10.1145/3613904.3641993 2024

  17. [17]

    Lee Anna Clark and David Watson. 2019. Constructing validity: New develop- ments in creating objective measuring instruments.Psychological Assessment 31, 12 (Dec. 2019), 1412–1427. doi:10.1037/pas0000626

    work page doi:10.1037/pas0000626 2019

  18. [18]

    1988.Statistical Power Analysis for the Behavioral Sciences(2nd ed.)

    Jacob Cohen. 1988.Statistical Power Analysis for the Behavioral Sciences(2nd ed.). Routledge, New York, NY. 567 pages. doi:10.4324/9780203771587

    work page doi:10.4324/9780203771587 1988

  19. [19]

    Andy Crabtree. 2025. H is for human and how (not) to evaluate qualitative research in HCI. 24 pages. doi:10.1080/07370024.2025.2475743

    work page doi:10.1080/07370024.2025.2475743 2025

  20. [20]

    Sylvain Daronnat, Leif Azzopardi, Martin Halvey, and Mateusz Dubiel. 2020. Impact of Agent Reliability and Predictability on Trust in Real Time Human- Agent Collaboration. InProceedings of the 8th International Conference on Human- Agent Interaction(Virtual Event, USA)(HAI ’20). Association for Computing Machinery, New York, NY, USA, 131–139. doi:10.1145/...

    work page doi:10.1145/3406499.3415063 2020

  21. [21]

    Sylvain Daronnat, Leif Azzopardi, Martin Halvey, and Mateusz Dubiel. 2021. Inferring Trust From Users’ Behaviours; Agents’ Predictability Positively Af- fects Trust, Task Performance and Cognitive Load in Human-Agent Real-Time Collaboration.Frontiers in Robotics and AI8 (July 2021), 642201. doi:10.3389/ frobt.2021.642201

    arXiv 2021

  22. [22]

    Peter Davey, Claire Peden, Esmita Charani, Charis Marwick, and Susan Michie

  23. [23]

    doi:10.1016/j.ijantimicag.2014.11.014

    Time for action—Improving the design and reporting of behaviour change interventions for antimicrobial stewardship in hospitals: Early findings from a systematic review.International Journal of Antimicrobial Agents45, 3 (2015), 203–212. doi:10.1016/j.ijantimicag.2014.11.014

    work page doi:10.1016/j.ijantimicag.2014.11.014 2015

  24. [24]

    What" and

    Edward L. Deci and Richard M. Ryan. 2000. The "What" and "Why" of Goal Pursuits: Human Needs and the Self-Determination of Behavior.Psychological Inquiry11, 4 (2000), 227–268. doi:10.1207/S15327965PLI1104_01

    work page doi:10.1207/s15327965pli1104_01 2000

  25. [25]

    Ron F Del Rosario, Klaudia Krawiecka, and Christian Schroeder de Witt. 2025. Architecting resilient llm agents: A guide to secure plan-then-execute imple- mentations. arXiv:2509.08646 [cs.CR] doi:10.48550/arXiv.2509.08646

    work page doi:10.48550/arxiv.2509.08646 2025

  26. [26]

    Huifang Du, Xuejing Feng, Jun Ma, Meng Wang, Shiyu Tao, Yijie Zhong, Yuan-Fang Li, and Haofen Wang. 2024. Towards Proactive Interactions for In-Vehicle Conversational Assistants Utilizing Large Language Models. arXiv:2403.09135 [cs.HC] doi:10.48550/arXiv.2403.09135

    work page doi:10.48550/arxiv.2403.09135 2024

  27. [27]

    Susan Farrell and Therese Fessenden. 2024. Field Studies. Nielsen Norman Group. https://www.nngroup.com/articles/field-studies/ Accessed: 2026-01-03

    2024

  28. [28]

    Yasmin Felberbaum. 2020. Enhancing Physical Activity of Walking and Dual- Tasking among Older Adults Using Personalized Navigation Practice. InExtended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems (Honolulu, HI, USA)(CHI EA ’20). Association for Computing Machinery, New York, NY, USA, 1–8. doi:10.1145/3334480.3375034

    work page doi:10.1145/3334480.3375034 2020

  29. [29]

    Yasmin Felberbaum, Joel Lanir, and Patrice L. Weiss. 2023. Designing Mobile Health Applications to Support Walking for Older Adults.International Journal of Environmental Research and Public Health20, 4 (2023), 3611. doi:10.3390/ ijerph20043611

    2023

  30. [30]

    Ghantasala, Nele Albers, Kristell M

    Ramya P. Ghantasala, Nele Albers, Kristell M. Penfornis, Milon H. M. van Vliet, and Willem-Paul Brinkman. 2023. Feasibility of Generating Structured Motivational Messages for Tailored Physical Activity Coaching.Frontiers in Digital Health5 (2023), 1215187. doi:10.3389/fdgth.2023.1215187

    work page doi:10.3389/fdgth.2023.1215187 2023

  31. [31]

    Tianqi Gu, Inhi Kim, and Graham Currie. 2019. To be or not to be dockless: Empirical analysis of dockless bikeshare development in China.Transportation Research Part A: Policy and Practice119 (2019), 122–147. doi:10.1016/j.tra.2018. 11.007

    work page doi:10.1016/j.tra.2018 2019

  32. [33]

    Hagger and Aleksandra Luszczynska

    Martin S. Hagger and Aleksandra Luszczynska. 2014. Implementation Intention and Action Planning Interventions in Health Contexts: State of the Research and Proposals for the Way Forward.Applied Psychology: Health and Well-Being 6, 1 (2014), 1–47. doi:10.1111/aphw.12017

    work page doi:10.1111/aphw.12017 2014

  33. [34]

    Wendy Hardeman, Julie Houghton, Kathleen Lane, Andy Jones, and Felix Naughton. 2019. A systematic review of just-in-time adaptive interventions (JI- TAIs) to promote physical activity.International Journal of Behavioral Nutrition and Physical Activity16, 1 (April 2019), 31. doi:10.1186/s12966-019-0792-7

    work page doi:10.1186/s12966-019-0792-7 2019

  34. [35]

    Tim Harries, Parisa Eslambolchilar, Chris Stride, Ruth Rettie, and Simon Walton

  35. [36]

    InHuman-Computer Interaction – INTERACT 2013

    Walking in the Wild – Using an Always-On Smartphone Application to Increase Physical Activity. InHuman-Computer Interaction – INTERACT 2013. Springer Berlin Heidelberg, Berlin, Heidelberg, 19–36. doi:10.1007/978-3-642- 40498-6_2

    work page doi:10.1007/978-3-642- 2013

  36. [37]

    Md Hasebul Hasan, Mahir Labib Dihan, Tanzima Hashem, Mohammed Eunus Ali, and Md Rizwan Parvez. 2025. MapAgent: A Hierarchical Agent for Geospa- tial Reasoning with Dynamic Map Tool Integration. arXiv:2509.05933 [cs.AI] https://arxiv.org/abs/2509.05933

    arXiv 2025

  37. [38]

    Marc Hassenzahl and Noam Tractinsky. 2006. User experience - a research agenda.Behaviour & Information Technology25, 2 (2006), 91–97. doi:10.1080/ 01449290500330331

    2006

  38. [39]

    Chenghua Huang, Shisong Chen, Zhixu Li, Jianfeng Qu, Yanghua Xiao, Jiaxin Liu, and Zhigang Chen. 2024. GeoAgent: To Empower LLMs using Geospatial Tools for Address Standardization. InFindings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics, Bangkok, Thailand, 6048–6063. doi:10.18653/v1/2024.findings-acl.362

    work page doi:10.18653/v1/2024.findings-acl.362 2024

  39. [40]

    Rossi, Branislav Kveton, Dongruo Zhou, Julian McAuley, and Lina Yao

    Chengkai Huang, Junda Wu, Yu Xia, Zixu Yu, Ruhan Wang, Tong Yu, Ruiyi Zhang, Ryan A. Rossi, Branislav Kveton, Dongruo Zhou, Julian McAuley, and Lina Yao. 2025. Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models. arXiv:2503.16734 [cs.AI] doi:10.48550/arXiv.2503.16734

    work page doi:10.48550/arxiv.2503.16734 2025

  40. [41]

    Kosuke Imai, Luke Keele, and Dustin Tingley. 2010. A General Approach to Causal Mediation Analysis.Psychological Methods15, 4 (Dec. 2010), 309–334. doi:10.1037/a0020761

    work page doi:10.1037/a0020761 2010

  41. [42]

    Byron Jones and Michael G. Kenward. 2014.Design and Analysis of Cross-Over Trials(3rd ed.). Chapman and Hall/CRC, New York. doi:10.1201/b17537

    work page doi:10.1201/b17537 2014

  42. [43]

    Kristian Møller Jørgensen. 2016. The media go-along: Researching mobilities with media at hand.MedieKultur: Journal of media and communication research 32, 60 (2016), 32–49

    2016

  43. [44]

    Matthew Jörke, Shardul Sapkota, Lyndsea Warkenthien, Niklas Vainio, Paul Schmiedmayer, Emma Brunskill, and James A. Landay. 2025. GPTCoach: Towards LLM-Based Physical Activity Coaching. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Associa- tion for Computing Machinery, New York, NY, USA, Article 993, 46 pages. ...

    work page doi:10.1145/3706598.3713819 2025

  44. [45]

    Yuka Kaniwa, Masaki Kuribayashi, Seita Kayukawa, Daisuke Sato, Hironobu Takagi, Chieko Asakawa, and Shigeo Morishima. 2024. ChitChatGuide: Conver- sational Interaction Using Large Language Models for Assisting People with Visual Impairments to Explore a Shopping Mall.Proc. ACM Hum.-Comput. Interact.8, MHCI, Article 247 (Sept. 2024), 25 pages. doi:10.1145/3676492

    work page doi:10.1145/3676492 2024

  45. [46]

    Joeun Kim, Youngjin Seo, Yeonsoo Kim, Junhyeok Kang, Jeeho Shin, Patara Trirat, and Jae-Gil Lee. 2025. Large language models are zero-shot point-of- interest recommenders.Data Mining and Knowledge Discovery39, 6 (2025), 80. doi:10.1007/s10618-025-01148-w

    work page doi:10.1007/s10618-025-01148-w 2025

  46. [47]

    Hekler, Saul Shiffman, Audrey Boruvka, Daniel Almirall, Ambuj Tewari, and Susan A

    Predrag Klasnja, Eric B. Hekler, Saul Shiffman, Audrey Boruvka, Daniel Almirall, Ambuj Tewari, and Susan A. Murphy. 2015. Micro-Randomized Trials: An Ex- perimental Design for Developing Just-in-Time Adaptive Interventions.Health Psychology34, Suppl (Dec. 2015), 1220–1228. doi:10.1037/hea0000305

    work page doi:10.1037/hea0000305 2015

  47. [48]

    Krukowski, Andrea H

    Rebecca A. Krukowski, Andrea H. Denton, and Laura M. König. 2024. Impact of feedback generation and presentation on self-monitoring behaviors, dietary intake, physical activity, and weight: a systematic review and meta-analysis. International Journal of Behavioral Nutrition and Physical Activity21, 1 (2024), 3. doi:10.1186/s12966-023-01555-6

    work page doi:10.1186/s12966-023-01555-6 2024

  48. [49]

    Ehsan Latif. 2024. 3P-LLM: Probabilistic Path Planning using Large Language Model for Autonomous Robot Navigation. arXiv:2403.18778 [cs.RO] doi:10. 48550/arXiv.2403.18778

    arXiv 2024

  49. [50]

    Chaehong Lee, Varatheepan Paramanayakam, Andreas Karatzas, Yanan Jian, Michael Fore, Heming Liao, Fuxun Yu, Ruopu Li, Iraklis Anagnostopoulos, and Dimitrios Stamoulis. 2025. Multi-Agent Geospatial Copilots for Remote Sensing Workflows. arXiv:2501.16254 [cs.LG] doi:10.48550/arXiv.2501.16254

    work page doi:10.48550/arxiv.2501.16254 2025

  50. [51]

    Huitian Lei, Yangyi Lu, Ambuj Tewari, and Susan A. Murphy. 2022. An Actor- Critic Contextual Bandit Algorithm for Personalized Mobile Health Interven- tions. arXiv:1706.09090 [stat.ML] doi:10.48550/arXiv.1706.09090

    work page doi:10.48550/arxiv.1706.09090 2022

  51. [52]

    Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. CAMEL: communicative agents for "mind" exploration of large language model society. InProceedings of the 37th International Confer- ence on Neural Information Processing Systems(New Orleans, LA, USA)(NIPS ’23). Curran Associates Inc., Red Hook, NY, USA, Artic...

    2023

  52. [53]

    Kechen Li, Yaotian Tao, Ximing Wen, Quanwei Sun, Zifei Gong, Chang Xu, Xizhe Zhang, and Tianbo Ji. 2025. GridRoute: A Benchmark for LLM-Based Route Plan- ning with Cardinal Movement in Grid Environments. arXiv:2505.24306 [cs.AI] doi:10.48550/arXiv.2505.24306

    work page doi:10.48550/arxiv.2505.24306 2025

  53. [54]

    Mingyuan Li, Duan Wang, Erick Purwanto, Thomas Selig, Qing Zhang, and Hai-Ning Liang. 2025. VisualCodeMOOC: A course platform for algorithms and data structures integrating a conversational agent for enhanced learning through dynamic visualizations.SoftwareX30 (2025), 102072. doi:10.1016/j. softx.2025.102072 IUI ’26, March 23–26, 2026, Paphos, Cyprus Zhang et al

    work page doi:10.1016/j 2025

  54. [55]

    Peng Liao, Kristjan Greenewald, Predrag Klasnja, and Susan Murphy. 2020. Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity.Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.4, 1, Article 18 (March 2020), 22 pages. doi:10.1145/3381007

    work page doi:10.1145/3381007 2020

  55. [56]

    Zhao Liu, Wei Liu, Huajie Zhu, Jianxing Yu, Jian Yin, Wang-Chien Lee, and Shun Wang. 2025. Geography-Aware Large Language Models for Next POI Recommendation. arXiv:2505.13526 [cs.IR] doi:10.48550/arXiv.2505.13526

    work page doi:10.48550/arxiv.2505.13526 2025

  56. [57]

    Tiffany Christina Luo, Adrian Aguilera, Courtney Rees Lyles, and Caro- line Astrid Figueroa. 2021. Promoting Physical Activity Through Conversational Agents: Mixed Methods Systematic Review.J Med Internet Res23, 9 (Sept. 2021), e25486. doi:10.2196/25486

    work page doi:10.2196/25486 2021

  57. [58]

    Mapbox. 2026. MapGPT: AI Assistant with Location Intelligence. https://www. mapbox.com/mapgpt. Accessed: 2026-01-03

    2026

  58. [59]

    Abhinav Mehrotra, Mirco Musolesi, Robert Hendley, and Veljko Pejovic. 2015. Designing content-driven intelligent notification mechanisms for mobile applica- tions. InProceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing(Osaka, Japan)(UbiComp ’15). Association for Com- puting Machinery, New York, NY, USA, 813–824....

    work page doi:10.1145/2750858.2807544 2015

  59. [60]

    Abhinav Mehrotra, Veljko Pejovic, Jo Vermeulen, Robert Hendley, and Mirco Musolesi. 2016. My Phone and Me: Understanding People’s Receptivity to Mobile Notifications. InProceedings of the 2016 CHI Conference on Human Factors in Computing Systems(San Jose, California, USA)(CHI ’16). Association for Computing Machinery, New York, NY, USA, 1021–1032. doi:10....

    work page doi:10.1145/2858036 2016

  60. [61]

    Silin Meng, Yiwei Wang, Cheng-Fu Yang, Nanyun Peng, and Kai-Wei Chang

  61. [62]

    InFindings of the Association for Computational Linguistics: EMNLP 2024

    LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning. InFindings of the Association for Computational Linguistics: EMNLP 2024. Association for Computational Linguistics, Miami, Florida, USA, 1087–1102. doi:10.18653/v1/2024.findings-emnlp.60

    work page doi:10.18653/v1/2024.findings-emnlp.60 2024

  62. [63]

    Morris and Adrianne E

    Jeremy N. Morris and Adrianne E. Hardman. 1997. Walking to Health.Sports Medicine23, 5 (May 1997), 306–332. doi:10.2165/00007256-199723050-00004

    work page doi:10.2165/00007256-199723050-00004 1997

  63. [64]

    Inbal Nahum-Shani, Shawna N Smith, Bonnie J Spring, Linda M Collins, Katie Witkiewitz, Ambuj Tewari, and Susan A Murphy. 2017. Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support.Annals of Behavioral Medicine52, 6 (Dec. 2017), 446–462. doi:10.1007/s12160-016-9830-8

    work page doi:10.1007/s12160-016-9830-8 2017

  64. [65]

    Michelle Ng, Elizabeth Wenden, Leanne Lester, Carri Westgarth, and Hayley Christian. 2022. A mobile health intervention to encourage physical activity in children: a randomised controlled trial.BMC Pediatrics22, 1 (May 2022), 276. doi:10.1186/s12887-022-03336-9

    work page doi:10.1186/s12887-022-03336-9 2022

  65. [66]

    Nowell, Jill M

    Lorelli S. Nowell, Jill M. Norris, Deborah E. White, and Nancy J. Moules. 2017. Thematic Analysis: Striving to Meet the Trustworthiness Criteria.International Journal of Qualitative Methods16, 1 (2017), 1609406917733847. doi:10.1177/ 1609406917733847

    2017

  66. [67]

    O’Brien, Paul Cairns, and Mark Hall

    Heather L. O’Brien, Paul Cairns, and Mark Hall. 2018. A practical approach to measuring user engagement with the refined user engagement scale (UES) and new UES short form.International Journal of Human-Computer Studies112 (2018), 28–39. doi:10.1016/j.ijhcs.2018.01.004

    work page doi:10.1016/j.ijhcs.2018.01.004 2018

  67. [68]

    Yoo Jung Oh, Kai-Hui Liang, Diane Dagyong Kim, Xuanming Zhang, Zhou Yu, Yoshimi Fukuoka, and Jingwen Zhang. 2025. Enhancing physical ac- tivity through a relational artificial intelligence chatbot: A feasibility and usability study.Digital Health11 (2025), 20552076251324445. doi:10.1177/ 20552076251324445

    2025

  68. [69]

    Yoo Jung Oh, Jingwen Zhang, Min-Lin Fang, and Yoshimi Fukuoka. 2021. A sys- tematic review of artificial intelligence chatbots for promoting physical activity, healthy diet, and weight loss.International Journal of Behavioral Nutrition and Physical Activity18, 1 (Dec. 2021), 160. doi:10.1186/s12966-021-01224-6

    work page doi:10.1186/s12966-021-01224-6 2021

  69. [70]

    Nelson Pacheco Rocha, Ana Dias, Gonçalo Santinha, Mário Rodrigues, Carlos Rodrigues, Alexandra Queirós, Rute Bastardo, and João Pavão. 2022. Systematic literature review of context-awareness applications supported by smart cities’ infrastructures.SN Applied Sciences4, 4 (2022), 90

    2022

  70. [71]

    Patel, Dylan S

    Mitesh S. Patel, Dylan S. Small, Joseph D. Harrison, Victoria Hilbert, Michael P. Fortunato, Ai Leen Oon, Charles A. L. Rareshide, and Kevin G. Volpp. 2021. Effect of Behaviorally Designed Gamification With Social Incentives on Lifestyle Modification Among Adults With Uncontrolled Diabetes: A Randomized Clinical Trial.JAMA Network Open4, 5 (May 2021), e21...

    arXiv 2021

  71. [72]

    Patil, Tianjun Zhang, Xin Wang, and Joseph E

    Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. 2024. Gorilla: Large Language Model Connected with Massive APIs. InAdvances in Neural Information Processing Systems, Vol. 37. Neural Information Processing Systems Foundation, Vancouver, Canada, 126544–126565. doi:10.52202/079017-4020

    work page doi:10.52202/079017-4020 2024

  72. [73]

    Xiaohan Peng, Janin Koch, and Wendy E. Mackay. 2025. FusAIn: Composing Generative AI Visual Prompts Using Pen-based Interaction. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 874, 20 pages. doi:10.1145/3706598.3714027

    work page doi:10.1145/3706598.3714027 2025

  73. [74]

    Martin Pielot, Karen Church, and Rodrigo de Oliveira. 2014. An in-situ study of mobile phone notifications. InProceedings of the 16th International Conference on Human-Computer Interaction with Mobile Devices & Services(Toronto, ON, Canada)(MobileHCI ’14). Association for Computing Machinery, New York, NY, USA, 233–242. doi:10.1145/2628363.2628364

    work page doi:10.1145/2628363.2628364 2014

  74. [75]

    Bogdan Popa. 2023. This Tool Converts Google Maps Into a Super-Advanced Navigation App You Can Talk To. autoevolution. https://www.autoevolution.com/news/this-tool-converts-google-maps- into-a-super-advanced-navigation-app-you-can-talk-to-217698.html Ac- cessed: 2026-01-03

    2023

  75. [76]

    Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou, Mark Gerstein, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2024. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs. InProceedings of the International Conferenc...

    2024

  76. [77]

    Behnam Rahdari and Peter Brusilovsky. 2025. From Links to Dialogue: Hyper- text Challenges and Opportunities in Conversational Navigation. InAdjunct Proceedings of the 36th ACM Conference on Hypertext and Social Media (HT Adjunct 2025)(Chicago, IL, USA). Association for Computing Machinery, New York, NY, USA, 25–29. doi:10.1145/3720533.3750064

    work page doi:10.1145/3720533.3750064 2025

  77. [78]

    Ryan and Edward L

    Richard M. Ryan and Edward L. Deci. 2022. Intrinsic Motivation Inventory (IMI): Instrument and Scoring Guide. https://selfdeterminationtheory.org/intrinsic- motivation-inventory/. Accessed: 2025-10-10

    2022

  78. [79]

    Iori Sasaki, Masatoshi Arikawa, Min Lu, Tomihiro Utsumi, and Ryo Sato. 2024. Data-Driven Geofencing Design for Point-of-Interest Notifiers Utilizing Genetic Algorithm.ISPRS International Journal of Geo-Information13, 6 (2024), 174. doi:10.3390/ijgi13060174

    work page doi:10.3390/ijgi13060174 2024

  79. [80]

    Timo Schick, Jane Dwivedi-Yu, Roberto Dessi, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language Models Can Teach Themselves to Use Tools. InAdvances in Neural Information Processing Systems, Vol. 36. Curran Associates, Inc., New Orleans, LA, USA, 68539–68551. https://proceedings.n...

    2023

  80. [81]

    Martin Schrepp, Andreas Hinderks, and Jörg Thomaschewski. 2017. Design and Evaluation of a Short Version of the User Experience Questionnaire (UEQ-S). International Journal of Interactive Multimedia and Artificial Intelligence4, 6 (2017), 103–108. doi:10.9781/ijimai.2017.09.001

    work page doi:10.9781/ijimai.2017.09.001 2017

Showing first 80 references.