# Generalizable Multi-Agent Planning from Signal Temporal Logic Specifications via Diffusion

arXiv: https://arxiv.org/abs/2608.29490 · HTML: https://mlsanity.com/paper/2608.29490/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 27 of 27)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning](https://mlsanity.com/paper/2010.03950/) (2020)
- [Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models](https://mlsanity.com/paper/2308.01557/) (2023)
- [Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates](https://mlsanity.com/paper/2101.05436/) (2021)
- [LTL2Action: Generalizing LTL Instructions for Multi-Task RL](https://mlsanity.com/paper/2102.06858/) (2021)
- [Policy-Guided Diffusion](https://mlsanity.com/paper/2404.06356/) (2024)
- [Multi-Robot Motion Planning with Diffusion Models](https://mlsanity.com/paper/2410.03072/) (2024)
- [Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations](https://mlsanity.com/paper/2408.04380/) (2024)
- [Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference](https://mlsanity.com/paper/2312.09608/) (2023)
- [GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Control](https://mlsanity.com/paper/2401.14554/) (2024)
- [Multi-agent Motion Planning from Signal Temporal Logic Specifications](https://mlsanity.com/paper/2201.05247/) (2022)
- [Learning from Demonstrations using Signal Temporal Logic](https://mlsanity.com/paper/2102.07730/) (2021)
- [Mixed-Integer Programming for Signal Temporal Logic with Fewer Binary Variables](https://mlsanity.com/paper/2204.06367/) (2022)
- [LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-based Planning](https://mlsanity.com/paper/2405.04235/) (2024)
- [Robust Counterexample-guided Optimization for Planning from Differentiable Temporal Logic](https://mlsanity.com/paper/2203.02038/) (2022)
- [TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching](https://mlsanity.com/paper/2505.00562/) (2025)
- [STLCG++: A Masking Approach for Differentiable Signal Temporal Logic Specification](https://mlsanity.com/paper/2501.04194/) (2025)
- [Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control](https://mlsanity.com/paper/2502.03640/) (2025)
- [Robust Multi-Agent Coordination from CaTL+ Specifications](https://mlsanity.com/paper/2210.01732/) (2022)
- [Model-free Neural Lyapunov Control for Safe Robot Navigation](https://mlsanity.com/paper/2203.01190/) (2022)
- [Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks](https://mlsanity.com/paper/2501.13457/) (2025)
- [Scaling Safe Multi-Agent Control for Signal Temporal Logic Specifications](https://mlsanity.com/paper/2501.05639/) (2025)
- [Efficient STL Control Synthesis under Asynchronous Temporal Robustness Constraints](https://mlsanity.com/paper/2307.12855/) (2023)
- [Scalable Multi-Robot Task Allocation and Coordination under Signal Temporal Logic Specifications](https://mlsanity.com/paper/2503.02719/) (2025)

## Abstract (arXiv)

Multi-agent systems in the real-world (e.g., drone swarms, autonomous cars, warehouse robots) must satisfy rich, temporal tasks while avoiding collisions. Signal Temporal Logic (STL) elegantly encodes such objectives, but current STL planning methods face critical limitations. State-of-the-art optimization-based approaches can handle arbitrary STL specifications but struggle with scalability, becoming computationally impractical as the number of agents grows. Learning-based methods efficiently handle a large number of agents with rapid planning times but fare poorly when deployment-time objectives differ from those used during training, and do not support planning tasks that require different specifications to be ascribed to different agents (i.e., heterogeneity) or team-level specifications requiring coordination of multiple agents. This fundamental trade-off between generalizability and scalability presents a challenge for realizing multi-agent STL planning algorithms in practice. To overcome this challenge, we introduce a new diffusion method for multi-agent planning with STL specifications. Using a differentiable approximation of STL, we integrate the STL gradient in the denoising process, making our approach generalizable to novel formulas whose predicates are placed anywhere within the goal region covered during training, while achieving the same scalability as existing learning-based methods. Our method supports heterogeneous specifications, and by using diffusion models, naturally enhances plan diversity, thereby significantly reducing safety-related violations (e.g., collisions) among agents. A detailed evaluation study justifies the utility of STL-guided diffusion-based multi-agent planners for constructing generalizable, scalable, and diverse plans. Videos and code are available at https://www.jeappen.com/diff-ma-stl/ and https://github.com/jeappen/diff-ma-stl .