pith. sign in

arxiv: 2503.12333 · v2 · submitted 2025-03-16 · 💻 cs.RO · cs.MA

GameChat: Multi-LLM Dialogue for Safe, Agile, and Socially Optimal Multi-Agent Navigation in Constrained Environments

Vagul Mahadevan , Shangtong Zhang , Rohan Chandra This is my paper

Pith reviewed 2026-05-23 00:50 UTC · model grok-4.3

classification 💻 cs.RO cs.MA
keywords multi-agent navigationLLM dialoguedecentralized roboticsconflict resolutionconstrained environmentsself-interested agents
0
0 comments X

The pith

Robots resolve navigation conflicts in tight spaces through natural language dialogue generated by their own LLMs.

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

The paper presents GameChat as a way for multiple agents to handle spatial conflicts in constrained settings like doorways and intersections by exchanging messages in natural language. Each agent runs its own LLM to generate and interpret these messages, allowing self-interested agents with private priorities to negotiate right-of-way without any central controller. The method is evaluated in simulations against naive and state-of-the-art baselines, with reported gains in completion time and priority adherence. The core idea is that this dialogue approach produces safer and more socially compliant paths than methods relying on predefined rules or explicit coordination protocols.

Core claim

GameChat enables agents to resolve conflicts induced by spatial symmetry through natural language communication generated by their individual LLMs, resulting in safe, agile, and socially compliant navigation for both cooperative and self-interested agents in cluttered environments such as doorways and intersections.

What carries the argument

GameChat, the multi-LLM dialogue system that lets agents communicate and negotiate priorities using natural language instead of central authority or fixed protocols.

If this is right

  • Reduces the time for all agents to reach their goals by over 35% from a naive baseline and over 20% from a state-of-the-art baseline in the intersection scenario.
  • Doubles the rate of ensuring the agent with a higher priority task reaches the goal first, from 50% to 100%.
  • Extends to scenarios involving more than two agents while preserving deadlock-free behavior.
  • Applies to both cooperative and self-interested agents without requiring changes to the underlying dialogue mechanism.

Where Pith is reading between the lines

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

  • Dialogue-based negotiation could reduce reliance on hand-crafted priority rules in other multi-robot tasks such as task allocation.
  • Performance in real hardware would depend on whether LLM responses remain coherent under communication delays or sensor noise.
  • The approach might scale to larger groups if dialogue length and turn-taking are bounded by additional rules.

Load-bearing premise

That LLM-generated natural language dialogue can reliably and safely resolve spatial conflicts and priority disputes among self-interested agents without central authority or explicit coordination protocols.

What would settle it

A recorded simulation run in an intersection where agents exchange dialogue messages yet still collide or enter a permanent deadlock.

Figures

Figures reproduced from arXiv: 2503.12333 by Rohan Chandra, Shangtong Zhang, Vagul Mahadevan.

Figure 1
Figure 1. Figure 1: Two agents head toward a hospital and a grocery store in a symmetric, constrained environment. Both agents need to get through the gap, but one must go in front or they will collide. In the left image, there is no communication between the agents, causing a deadlock as the agents do not know which should go first, and in the right image, GAMECHAT uses natural language communication between decentralized ag… view at source ↗
Figure 2
Figure 2. Figure 2: Example of a social mini-game. Each agent (represented by the red [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Flow chart describing the logical flow of G [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Simplified game tree. Each arrow represents a possible combination [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Trajectories generated by noncommunicative methods in the [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Trajectories generated by noncommunicative methods in symmetric [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 8
Figure 8. Figure 8: GAMECHAT trajectories in intersection environment. Blue is a grocery agent and red is a hospital agent. Top row is pre-SMG conversation in symmetric environment, second is during SMG conversation in symmetric, third is pre-SMG with asymmetric, and fourth is during SMG with asymmetric. The conversation finished at t = 2.48 for the symmetric (second row) and at t = 2.61 for the asymmetric (fourth row). the n… view at source ↗
read the original abstract

Safe, agile, and socially compliant multi-robot navigation in cluttered and constrained environments remains a critical challenge. This is especially difficult with self-interested agents with unique, unknown priorities in decentralized settings, where there is no central authority to resolve conflicts induced by spatial symmetry. We address this challenge by proposing an intuitive, but very effective approach, GameChat, which facilitates safe, agile, and deadlock-free navigation for both cooperative and self-interested agents in cluttered environments. Key to our approach is the idea that agents should resolve conflicts on their own using natural language to communicate, much like humans. We evaluate GameChat in simulated environments with doorways and intersections. The results show that even in the worst case, GameChat reduces the time for all agents to reach their goals by over 35% from a naive baseline and by over 20% from a state of the art baseline in the intersection scenario, while doubling the rate of ensuring the agent with a higher priority task reaches the goal first, from 50% (equivalent to random chance) to 100%. We also demonstrate how GameChat can be extended to more than two agents.

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

1 major / 1 minor

Summary. The manuscript proposes GameChat, a decentralized multi-agent navigation method in which multiple LLMs enable agents to communicate via natural language dialogue to resolve spatial conflicts and priority disputes in constrained settings such as doorways and intersections. The approach is evaluated in simulation for both cooperative and self-interested agents, reporting time-to-goal reductions of over 35% versus a naive baseline and over 20% versus a state-of-the-art baseline in the intersection case, together with an increase in higher-priority task success from 50% to 100%. The method is also shown to scale to more than two agents.

Significance. If the empirical results hold under full methodological scrutiny, the work would be significant for decentralized multi-robot systems by demonstrating that LLM-mediated natural language negotiation can produce measurable gains in navigation efficiency and social compliance without central coordination. The concrete percentage improvements and the extension to multi-agent cases provide a reproducible benchmark that could stimulate further research on dialogue-based conflict resolution in robotics.

major comments (1)
  1. [Abstract] Abstract: the central claim that GameChat achieves 100% success in ensuring the higher-priority agent reaches its goal first (versus 50% for random) is load-bearing for the 'socially optimal' contribution. The abstract provides no information on how task priorities are encoded, communicated, or enforced within the LLM dialogue, nor on the simulation assumptions that could produce this outcome; without these details the result cannot be assessed for robustness.
minor comments (1)
  1. The abstract refers to 'a state of the art baseline' without naming the method; this comparison should be specified with a citation or description in the evaluation section.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the positive evaluation and constructive comment. We agree that the abstract would benefit from added context on priority handling to support the reported results, and we will revise accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that GameChat achieves 100% success in ensuring the higher-priority agent reaches its goal first (versus 50% for random) is load-bearing for the 'socially optimal' contribution. The abstract provides no information on how task priorities are encoded, communicated, or enforced within the LLM dialogue, nor on the simulation assumptions that could produce this outcome; without these details the result cannot be assessed for robustness.

    Authors: We agree the abstract is concise and omits key details on priority handling. In the revised version we will expand the abstract by one sentence to state that each agent is provided with a numerical priority value, that agents communicate these values and negotiate via natural language (e.g., “I have higher priority, please yield”), and that the LLM is prompted to resolve conflicts by deferring to the higher-priority agent. The simulation assumes truthful priority reporting and that the LLM follows the priority rule without deviation. These mechanisms are fully specified in Sections 3.2 and 4.1 with prompt templates and dialogue traces; the abstract revision will reference those sections. This change addresses the robustness concern without altering any empirical claims. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper describes an empirical multi-agent navigation system evaluated via simulation against external baselines (naive and state-of-the-art). No mathematical derivation chain, fitted parameters renamed as predictions, or load-bearing self-citations appear in the provided material; performance metrics are reported as direct simulation outcomes rather than reductions to the method's own inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Based solely on the abstract, the central claim rests on the domain assumption that natural language communication via LLMs can substitute for explicit protocols in resolving spatial symmetry conflicts; no free parameters or invented entities are identifiable from the provided text.

axioms (1)
  • domain assumption LLM dialogue can reliably resolve conflicts and enforce priorities among self-interested agents in decentralized settings
    This premise is invoked as the key idea enabling safe navigation without central authority.

pith-pipeline@v0.9.0 · 5743 in / 1201 out tokens · 35950 ms · 2026-05-23T00:50:49.262371+00:00 · methodology

discussion (0)

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

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Large Language Models for Multi-Robot Systems: A Survey

    cs.RO 2025-02 unverdicted novelty 4.0

    A survey that categorizes LLM uses in multi-robot systems across task allocation, motion planning, action generation, and human interaction, while noting challenges and future research opportunities.

Reference graph

Works this paper leans on

59 extracted references · 59 canonical work pages · cited by 1 Pith paper · 2 internal anchors

  1. [1]

    A review of mobile robots: Applications and future prospect,

    N. Sharma, J. K. Pandey, and S. Mondal, “A review of mobile robots: Applications and future prospect,” International Journal of Precision Engineering and Manufacturing, vol. 24, no. 9, pp. 1695–1706, 2023

    work page 2023

  2. [2]

    Deadlock- free, safe, and decentralized multi-robot navigation in social mini- games via discrete-time control barrier functions,

    R. Chandra, V . Zinage, E. Bakolas, P. Stone, and J. Biswas, “Deadlock- free, safe, and decentralized multi-robot navigation in social mini- games via discrete-time control barrier functions,” arXiv preprint arXiv:2308.10966, 2023

    work page arXiv 2023

  3. [3]

    Socialmapf: Optimal and efficient multi-agent path finding with strategic agents for social navigation,

    R. Chandra, R. Maligi, A. Anantula, and J. Biswas, “Socialmapf: Optimal and efficient multi-agent path finding with strategic agents for social navigation,” IEEE Robotics and Automation Letters , vol. 8, no. 6, pp. 3214–3221, 2023

    work page 2023

  4. [4]

    Gameplan: Game-theoretic multi- agent planning with human drivers at intersections, roundabouts, and merging,

    R. Chandra and D. Manocha, “Gameplan: Game-theoretic multi- agent planning with human drivers at intersections, roundabouts, and merging,” IEEE Robotics and Automation Letters , vol. 7, no. 2, pp. 2676–2683, 2022

    work page 2022

  5. [5]

    Rethinking social robot navigation: Leveraging the best of two worlds,

    A. H. Raj, Z. Hu, H. Karnan, R. Chandra, A. Payandeh, L. Mao, P. Stone, J. Biswas, and X. Xiao, “Rethinking social robot navigation: Leveraging the best of two worlds,” in 2024 IEEE International Conference on Robotics and Automation (ICRA) , pp. 16330–16337, IEEE, 2024

    work page 2024

  6. [6]

    Principles and guidelines for evaluating social robot navigation algorithms,

    A. Francis, C. P ´erez-d’Arpino, C. Li, F. Xia, A. Alahi, R. Alami, A. Bera, A. Biswas, J. Biswas, R. Chandra, et al. , “Principles and guidelines for evaluating social robot navigation algorithms,” arXiv preprint arXiv:2306.16740, 2023

    work page arXiv 2023

  7. [7]

    Multi-agent planning for non- cooperative agents.,

    C. Witteveen and M. de Weerdt, “Multi-agent planning for non- cooperative agents.,” in AAAI Spring Symposium: Distributed Plan and Schedule Management , p. 169, 2006

    work page 2006

  8. [8]

    Gameopt: Optimal real-time multi-agent planning and control for dynamic inter- sections,

    N. Suriyarachchi, R. Chandra, J. S. Baras, and D. Manocha, “Gameopt: Optimal real-time multi-agent planning and control for dynamic inter- sections,” in 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) , pp. 2599–2606, IEEE, 2022

    work page 2022

  9. [9]

    Gameopt+: Improving fuel efficiency in unregulated heterogeneous traffic intersections via optimal multi-agent cooperative control,

    N. Suriyarachchi, R. Chandra, A. Anantula, J. S. Baras, and D. Manocha, “Gameopt+: Improving fuel efficiency in unregulated heterogeneous traffic intersections via optimal multi-agent cooperative control,” arXiv preprint arXiv:2405.16430 , 2024

    work page arXiv 2024

  10. [10]

    The before, during, and after of multi-robot deadlock,

    J. Grover, C. Liu, and K. Sycara, “The before, during, and after of multi-robot deadlock,” The International Journal of Robotics Re- search, vol. 42, no. 6, pp. 317–336, 2023

    work page 2023

  11. [11]

    Fast, on- line collision avoidance for dynamic vehicles using buffered voronoi cells,

    D. Zhou, Z. Wang, S. Bandyopadhyay, and M. Schwager, “Fast, on- line collision avoidance for dynamic vehicles using buffered voronoi cells,” IEEE Robotics and Automation Letters, vol. 2, no. 2, pp. 1047– 1054, 2017

    work page 2017

  12. [12]

    Algames: a fast augmented lagrangian solver for constrained dynamic games,

    S. Le Cleac’h, M. Schwager, and Z. Manchester, “Algames: a fast augmented lagrangian solver for constrained dynamic games,” Au- tonomous Robots, vol. 46, no. 1, pp. 201–215, 2022

    work page 2022

  13. [13]

    Game- theoretic planning for autonomous driving among risk-aware human drivers,

    R. Chandra, M. Wang, M. Schwager, and D. Manocha, “Game- theoretic planning for autonomous driving among risk-aware human drivers,” in 2022 International Conference on Robotics and Automa- tion (ICRA), pp. 2876–2883, 2022

    work page 2022

  14. [14]

    Towards imitation learning in real world unstructured social mini-games in pedestrian crowds,

    R. Chandra, H. Karnan, N. Mehr, P. Stone, and J. Biswas, “Towards imitation learning in real world unstructured social mini-games in pedestrian crowds,” arXiv preprint arXiv:2405.16439 , 2024

    work page arXiv 2024

  15. [15]

    Efficient constrained multi-agent trajectory optimization using dynamic potential games,

    M. Bhatt, Y . Jia, and N. Mehr, “Efficient constrained multi-agent trajectory optimization using dynamic potential games,” in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7303–7310, IEEE, 2023

    work page 2023

  16. [16]

    Cmetric: A driving behavior measure using centrality functions,

    R. Chandra, U. Bhattacharya, T. Mittal, A. Bera, and D. Manocha, “Cmetric: A driving behavior measure using centrality functions,” in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2035–2042, IEEE, 2020

    work page 2020

  17. [17]

    Graphrqi: Classifying driver behaviors using graph spectrums,

    R. Chandra, U. Bhattacharya, T. Mittal, X. Li, A. Bera, and D. Manocha, “Graphrqi: Classifying driver behaviors using graph spectrums,” in 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 4350–4357, IEEE, 2020

    work page 2020

  18. [18]

    Using graph-theoretic ma- chine learning to predict human driver behavior,

    R. Chandra, A. Bera, and D. Manocha, “Using graph-theoretic ma- chine learning to predict human driver behavior,” IEEE Transactions on Intelligent Transportation Systems , vol. 23, no. 3, pp. 2572–2585, 2021

    work page 2021

  19. [19]

    Intent- aware planning in heterogeneous traffic via distributed multi-agent reinforcement learning,

    X. Wu, R. Chandra, T. Guan, A. Bedi, and D. Manocha, “Intent- aware planning in heterogeneous traffic via distributed multi-agent reinforcement learning,” in Conference on Robot Learning , pp. 446– 477, PMLR, 2023

    work page 2023

  20. [20]

    Spieltheoretische behandlung eines oligopolmodells mit nachfragetr¨agheit: Teil i: Bestimmung des dynamischen preisgle- ichgewichts,

    R. Selten, “Spieltheoretische behandlung eines oligopolmodells mit nachfragetr¨agheit: Teil i: Bestimmung des dynamischen preisgle- ichgewichts,” Zeitschrift f ¨ur die gesamte Staatswissenschaft/Journal of Institutional and Theoretical Economics , no. H. 2, pp. 301–324, 1965

    work page 1965

  21. [21]

    Control barrier functions: Theory and applications,

    A. D. Ames, S. Coogan, M. Egerstedt, G. Notomista, K. Sreenath, and P. Tabuada, “Control barrier functions: Theory and applications,” in 2019 18th European control conference (ECC) , pp. 3420–3431, Ieee, 2019

    work page 2019

  22. [22]

    Reciprocal n-body collision avoidance,

    J. Van Den Berg, S. J. Guy, M. Lin, and D. Manocha, “Reciprocal n-body collision avoidance,” in Robotics Research: The 14th Interna- tional Symposium ISRR , pp. 3–19, Springer, 2011

    work page 2011

  23. [23]

    Distributed multi-agent navigation based on reciprocal collision avoidance and locally confined multi- agent path finding,

    S. Dergachev and K. Yakovlev, “Distributed multi-agent navigation based on reciprocal collision avoidance and locally confined multi- agent path finding,” in 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE) , pp. 1489–1494, IEEE, 2021

    work page 2021

  24. [24]

    Safety barrier certificates for collisions-free multirobot systems,

    L. Wang, A. D. Ames, and M. Egerstedt, “Safety barrier certificates for collisions-free multirobot systems,” IEEE Transactions on Robotics , vol. 33, no. 3, pp. 661–674, 2017

    work page 2017

  25. [25]

    Decentralized safe and scalable multi-agent control under limited actuation,

    V . Zinage, A. Jha, R. Chandra, and E. Bakolas, “Decentralized safe and scalable multi-agent control under limited actuation,” arXiv preprint arXiv:2409.09573, 2024

    work page arXiv 2024

  26. [26]

    Neural differentiable integral control barrier functions for unknown nonlinear systems with input constraints,

    V . Zinage, R. Chandra, and E. Bakolas, “Neural differentiable integral control barrier functions for unknown nonlinear systems with input constraints,” arXiv preprint arXiv:2312.07345 , 2023

    work page arXiv 2023

  27. [27]

    Safety-critical model predictive control with discrete-time control barrier function,

    J. Zeng, B. Zhang, and K. Sreenath, “Safety-critical model predictive control with discrete-time control barrier function,” in 2021 American Control Conference (ACC), pp. 3882–3889, IEEE, 2021

    work page 2021

  28. [28]

    Optimal reciprocal collision avoidance for multiple non- holonomic robots,

    J. Alonso-Mora, A. Breitenmoser, M. Rufli, P. Beardsley, and R. Sieg- wart, “Optimal reciprocal collision avoidance for multiple non- holonomic robots,” in Distributed autonomous robotic systems: The 10th international symposium , pp. 203–216, Springer, 2013

    work page 2013

  29. [29]

    Recursive feasibility and deadlock reso- lution in mpc-based multi-robot trajectory generation,

    Y . Chen, M. Guo, and Z. Li, “Recursive feasibility and deadlock reso- lution in mpc-based multi-robot trajectory generation,” arXiv preprint arXiv:2202.06071, 2022

    work page arXiv 2022

  30. [30]

    Autonomous and semiau- tonomous intersection management: A survey,

    Z. Zhong, M. Nejad, and E. E. Lee, “Autonomous and semiau- tonomous intersection management: A survey,”IEEE Intelligent Trans- portation Systems Magazine , vol. 13, no. 2, pp. 53–70, 2020

    work page 2020

  31. [31]

    Autonomous intersection man- agement for semi-autonomous vehicles,

    T.-C. Au, S. Zhang, and P. Stone, “Autonomous intersection man- agement for semi-autonomous vehicles,” in Routledge Handbook of Transportation, pp. 88–104, Routledge, 2015

    work page 2015

  32. [32]

    Auction-based autonomous intersection management,

    D. Carlino, S. D. Boyles, and P. Stone, “Auction-based autonomous intersection management,” in 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013) , pp. 529–534, IEEE, 2013

    work page 2013

  33. [33]

    A multiagent approach to autonomous intersection management,

    K. Dresner and P. Stone, “A multiagent approach to autonomous intersection management,” Journal of artificial intelligence research , vol. 31, pp. 591–656, 2008

    work page 2008

  34. [34]

    Motion planning and control for mobile robot navigation using machine learning: a survey,

    X. Xiao, B. Liu, G. Warnell, and P. Stone, “Motion planning and control for mobile robot navigation using machine learning: a survey,” Autonomous Robots, vol. 46, no. 5, pp. 569–597, 2022

    work page 2022

  35. [35]

    To- wards optimally decentralized multi-robot collision avoidance via deep reinforcement learning,

    P. Long, T. Fan, X. Liao, W. Liu, H. Zhang, and J. Pan, “To- wards optimally decentralized multi-robot collision avoidance via deep reinforcement learning,” in 2018 IEEE international conference on robotics and automation (ICRA) , pp. 6252–6259, IEEE, 2018

    work page 2018

  36. [36]

    Livenet: Robust, minimally invasive multi-robot control for safe and live navigation in constrained environments,

    S. Gouru, S. Lakkoju, and R. Chandra, “Livenet: Robust, minimally invasive multi-robot control for safe and live navigation in constrained environments,” arXiv preprint arXiv:2412.04659 , 2024

    work page arXiv 2024

  37. [37]

    Game- theoretic planning for self-driving cars in multivehicle competitive scenarios,

    M. Wang, Z. Wang, J. Talbot, J. C. Gerdes, and M. Schwager, “Game- theoretic planning for self-driving cars in multivehicle competitive scenarios,” IEEE Transactions on Robotics , vol. 37, no. 4, pp. 1313– 1325, 2021

    work page 2021

  38. [38]

    Numerical solution of potential games arising in the control of cooperative automatic vehicles,

    A. Britzelmeier, A. Dreves, and M. Gerdts, “Numerical solution of potential games arising in the control of cooperative automatic vehicles,” in 2019 Proceedings of the conference on control and its applications, pp. 38–45, SIAM, 2019

    work page 2019

  39. [39]

    Differential Dynamic Programming for Nonlinear Dynamic Games

    B. Di and A. Lamperski, “Differential dynamic programming for nonlinear dynamic games,” arXiv preprint arXiv:1809.08302 , 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  40. [40]

    Newton’s method and differential dynamic programming for unconstrained nonlinear dynamic games,

    B. Di and A. Lamperski, “Newton’s method and differential dynamic programming for unconstrained nonlinear dynamic games,” in 2019 IEEE 58th conference on decision and control (CDC), pp. 4073–4078, IEEE, 2019

    work page 2019

  41. [41]

    Decentralized path planning for multi-agent teams in complex environments using rapidly-exploring random trees,

    V . R. Desaraju and J. P. How, “Decentralized path planning for multi-agent teams in complex environments using rapidly-exploring random trees,” in 2011 IEEE international conference on robotics and automation, pp. 4956–4961, IEEE, 2011

    work page 2011

  42. [42]

    Resilient consensus for time-varying networks of dynamic agents,

    D. Saldana, A. Prorok, S. Sundaram, M. F. Campos, and V . Kumar, “Resilient consensus for time-varying networks of dynamic agents,” in 2017 American control conference (ACC) , pp. 252–258, IEEE, 2017

    work page 2017

  43. [43]

    Graph neural networks for decentralized multi-robot path planning,

    Q. Li, F. Gama, A. Ribeiro, and A. Prorok, “Graph neural networks for decentralized multi-robot path planning,” in 2020 IEEE/RSJ interna- tional conference on intelligent robots and systems (IROS), pp. 11785– 11792, IEEE, 2020

    work page 2020

  44. [44]

    Learning scalable and efficient communication policies for multi-robot collision avoidance,

    ´A. Serra-G ´omez, H. Zhu, B. Brito, W. B ¨ohmer, and J. Alonso- Mora, “Learning scalable and efficient communication policies for multi-robot collision avoidance,” Autonomous Robots, vol. 47, no. 8, pp. 1275–1297, 2023

    work page 2023

  45. [45]

    Dmca: Dense multi- agent navigation using attention and communication,

    S. H. Arul, A. S. Bedi, and D. Manocha, “Dmca: Dense multi- agent navigation using attention and communication,” arXiv preprint arXiv:2209.06415, 2022

    work page arXiv 2022

  46. [46]

    When, what, and with whom to communicate: Enhancing rl-based multi-robot navigation through selective communication,

    S. H. Arul, A. S. Bedi, and D. Manocha, “When, what, and with whom to communicate: Enhancing rl-based multi-robot navigation through selective communication,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7695–7695, IEEE, 2024

    work page 2024

  47. [47]

    Progprompt: Generating situated robot task plans using large language models,

    I. Singh, V . Blukis, A. Mousavian, A. Goyal, D. Xu, J. Tremblay, D. Fox, J. Thomason, and A. Garg, “Progprompt: Generating situated robot task plans using large language models,” in 2023 IEEE Inter- national Conference on Robotics and Automation (ICRA) , pp. 11523– 11530, IEEE, 2023

    work page 2023

  48. [48]

    Text2motion: From natural language instructions to feasible plans,

    K. Lin, C. Agia, T. Migimatsu, M. Pavone, and J. Bohg, “Text2motion: From natural language instructions to feasible plans,” Autonomous Robots, vol. 47, no. 8, pp. 1345–1365, 2023

    work page 2023

  49. [49]

    Foundation Models to the Rescue: Deadlock Resolution in Connected Multi-Robot Systems

    K. Garg, S. Zhang, J. Arkin, and C. Fan, “Foundation models to the rescue: Deadlock resolution in connected multi-robot systems,” arXiv preprint arXiv:2404.06413, 2024

    work page arXiv 2024

  50. [50]

    Language-Conditioned Offline RL for Multi-Robot Navigation

    S. Morad, A. Shankar, J. Blumenkamp, and A. Prorok, “Language- conditioned offline rl for multi-robot navigation,” arXiv preprint arXiv:2407.20164, 2024

    work page arXiv 2024

  51. [51]

    Socially aware robot navigation through scoring using vision-language models,

    D. Song, J. Liang, A. Payandeh, X. Xiao, and D. Manocha, “Socially aware robot navigation through scoring using vision-language models,” arXiv e-prints, pp. arXiv–2404, 2024

    work page 2024

  52. [52]

    Roco: Dialectic multi-robot col- laboration with large language models,

    Z. Mandi, S. Jain, and S. Song, “Roco: Dialectic multi-robot col- laboration with large language models,” in 2024 IEEE International Conference on Robotics and Automation (ICRA) , pp. 286–299, IEEE, 2024

    work page 2024

  53. [53]

    Dynamic pro- gramming for partially observable stochastic games,

    E. A. Hansen, D. S. Bernstein, and S. Zilberstein, “Dynamic pro- gramming for partially observable stochastic games,” in AAAI, vol. 4, pp. 709–715, 2004

    work page 2004

  54. [54]

    Cardinal welfare, individualistic ethics, and interper- sonal comparisons of utility,

    J. C. Harsanyi, “Cardinal welfare, individualistic ethics, and interper- sonal comparisons of utility,” Journal of political economy , vol. 63, no. 4, pp. 309–321, 1955

    work page 1955

  55. [55]

    GPT-4o System Card

    A. Hurst, A. Lerer, A. P. Goucher, A. Perelman, A. Ramesh, A. Clark, A. Ostrow, A. Welihinda, A. Hayes, A. Radford,et al., “Gpt-4o system card,” arXiv preprint arXiv:2410.21276 , 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  56. [56]

    The experimental study of social preferences,

    M. Rabin, “The experimental study of social preferences,” Social Research: An International Quarterly , vol. 73, no. 2, pp. 405–428, 2006

    work page 2006

  57. [57]

    do-mpc: Towards fair nonlinear and robust model predictive control,

    F. Fiedler, B. Karg, L. L ¨uken, D. Brandner, M. Heinlein, F. Brabender, and S. Lucia, “do-mpc: Towards fair nonlinear and robust model predictive control,”Control Engineering Practice, vol. 140, p. 105676, 2023

    work page 2023

  58. [58]

    Casadi: a software framework for nonlinear optimization and optimal control,

    J. A. Andersson, J. Gillis, G. Horn, J. B. Rawlings, and M. Diehl, “Casadi: a software framework for nonlinear optimization and optimal control,” Mathematical Programming Computation, vol. 11, pp. 1–36, 2019

    work page 2019

  59. [59]

    On the implementation of an interior- point filter line-search algorithm for large-scale nonlinear program- ming,

    A. W ¨achter and L. T. Biegler, “On the implementation of an interior- point filter line-search algorithm for large-scale nonlinear program- ming,” Mathematical programming, vol. 106, pp. 25–57, 2006

    work page 2006