{"slug": "ma-safediffuser-safe-multi-agent-planning-with-diffusion-probabilistic-models", "title": "MA-SafeDiffuser: Safe Multi-Agent Planning with Diffusion Probabilistic Models", "summary": "A new arXiv paper (2611.05524v1) introduces MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that gives diffusion-based trajectory planners finite-time diffusion invariance guarantees for joint-agent safety specifications. The work formalizes joint safe sets as intersections of per-agent and pairwise barrier sets, derives centralized and decentralized communication-aware constrained denoising procedures with provable invariance under mild assumptions, and addresses local-trap and deadlock phenomena via time-varying specifications and liveness control barrier functions. The authors report that MA-SafeDiffuser reduces violation counts relative to unconstrained diffusion baselines while retaining planning quality, and they release algorithms, proofs, a reference implementation, and a benchmarking suite including a multi-agent Maze2D domain.", "body_md": "arXiv:2611.05524v1 Announce Type: new \nAbstract: We propose MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that equips diffusion-based trajectory planners with finite-time diffusion invariance guarantees for joint-agent safety specifications. Building on the single-agent construction that embeds control barrier function (CBF) constraints into reverse-diffusion updates, we: (i) formalize joint safe sets as intersections of per-agent and pairwise barrier sets; (ii) derive centralized and decentralized (communication-aware) constrained denoising procedures with provable invariance under mild assumptions; (iii) address local-trap and deadlock phenomena via time-varying specifications and liveness CBFs; and (iv) develop a lightweight benchmarking suite including a multi-agent Maze2D domain. Empirically, MA-SafeDiffuser reduces violation counts relative to unconstrained diffusion baselines, while retaining planning quality. We provide algorithms, proofs, and reference implementations.", "url": "https://wpnews.pro/news/ma-safediffuser-safe-multi-agent-planning-with-diffusion-probabilistic-models", "canonical_source": "https://arxiv.org/abs/2611.05524", "published_at": "2026-11-05 05:00:00+00:00", "updated_at": "2026-11-05 05:21:33.399976+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-safety", "ai-research", "machine-learning"], "entities": ["MA-SafeDiffuser", "SafeDiffuser", "arXiv", "Maze2D"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/ma-safediffuser-safe-multi-agent-planning-with-diffusion-probabilistic-models", "markdown": "https://wpnews.pro/news/ma-safediffuser-safe-multi-agent-planning-with-diffusion-probabilistic-models.md", "text": "https://wpnews.pro/news/ma-safediffuser-safe-multi-agent-planning-with-diffusion-probabilistic-models.txt", "jsonld": "https://wpnews.pro/news/ma-safediffuser-safe-multi-agent-planning-with-diffusion-probabilistic-models.jsonld"}}