论文研究
arxiv.org ·
M³P-R1：通过 MIP 代码生成实现大语言模型引导的多模态运动规划的强化学习
该论文针对多模态运动规划（M³P）中连续运动与离散模式切换联合推理困难的问题，提出 M³P-R1：用强化学习微调大语言模型，把 M³P 任务分解为混合整数规划（MIP）的变量、约束与目标，并生成调用 MIP 优化库与约束接口的可执行 Python 代码，由求解器执行以获得可验证解。模型以求解器结果为奖励信号训练，学习组合模态级离散化原语并合成跨模态耦合约束。摘要未给出实验数据与性能对比。
AI推荐理由 arXiv 新提交论文（cs.RO），摘要明确给出方法动机、技术路线与训练信号：用强化学习微调 LLM，将多模态运动规划任务分解为 MIP 变量、约束和目标，并生成可执行的 Python 代码交由求解器验证，而非直接输出答案。对 LLM+机器人规划、代码生成与可验证求解方向有参考价值。局限在于仅有摘要，未提供实验数据、基线对比或成功率，实际效果无法确认。
72
正文
Computer Science > Robotics
arXiv:2609.18669 (cs)
[Submitted on 16 Sep 2026]
Title:M$^3$P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation
Authors:Xingpeng Sun, Zherong Pan, Kai Cheng, Xindi Tang, Syed Talha Bukhari, Aniket Bera
View a PDF of the paper titled M$^3$P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation, by Xingpeng Sun and 5 other authors
View PDF
HTML (experimental)
Abstract:Multi-Modal Motion Planning (M$^3$P) requires joint reasoning over continuous motions and discrete mode transitions, making it difficult to solve efficiently. For instance, a bipedal robot may walk to a target location and then use its arms to grasp an object. This scenario captures both mode transitions and continuous dynamics, yielding feasible paths that neither purely discrete nor continuous planners can handle. While Mixed-Integer Programming (MIP) offers a principled framework, constructing tractable formulations for non-convex problems is typically manual and domain-specific, especially in the approximate, discretization-based MIP regime needed for non-convex robotic tasks. We propose M$^3$P-R1, a reinforcement learning method that fine-tunes large language models (LLMs) to decompose M$^3$P tasks into MIP variables, constraints, and objectives. Instead of directly outputting answers, which are often prone to hallucination, the model generates executable Python code using MIP optimization libraries and constraint interfaces. This enables solver-backed execution for robust and verifiable solutions. Trained with an outcome-driven reward against the solver, M$^3$P-R1 learns to compose modality-level discretization primitives and synthesize cross-modal coupling constraints, producing executable MIP programs for complex M$^3$P tasks.
Comments:
Subjects:
Robotics (cs.RO)
Cite as:
arXiv:2609.18669 [cs.RO]
(or
arXiv:2609.18669v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.18669
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Xingpeng Sun [view email]
[v1]
Wed, 16 Sep 2026 13:47:13 UTC (13,806 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled M$^3$P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation, by Xingpeng Sun and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)