Pith. sign in

REVIEW 10 cited by

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.10775 v3 pith:TUKW3237 submitted 2024-04-16 cs.CV cs.AIcs.MA

classification cs.CVcs.AIcs.MA
keywords worldagentsactionscompositionalcooperationegocentricembodiedgiven
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we investigate the problem of embodied multi-agent cooperation, where decentralized agents must cooperate given only egocentric views of the world. To effectively plan in this setting, in contrast to learning world dynamics in a single-agent scenario, we must simulate world dynamics conditioned on an arbitrary number of agents' actions given only partial egocentric visual observations of the world. To address this issue of partial observability, we first train generative models to estimate the overall world state given partial egocentric observations. To enable accurate simulation of multiple sets of actions on this world state, we then propose to learn a compositional world model for multi-agent cooperation by factorizing the naturally composable joint actions of multiple agents and compositionally generating the video conditioned on the world state. By leveraging this compositional world model, in combination with Vision Language Models to infer the actions of other agents, we can use a tree search procedure to integrate these modules and facilitate online cooperative planning. We evaluate our methods on three challenging benchmarks with 2-4 agents. The results show our compositional world model is effective and the framework enables the embodied agents to cooperate efficiently with different agents across various tasks and an arbitrary number of agents, showing the promising future of our proposed methods. More videos can be found at https://umass-embodied-agi.github.io/COMBO/.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Sentinel: Embodied Cooperative Spatial Reasoning and Planning

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    Introduces Sentinel Challenge benchmark and CoSaR framework for cooperative spatial reasoning and planning among 3-5 decentralized embodied agents across 14 city-scale scenes.

  2. 3D-Belief: Embodied Belief Inference via Generative 3D World Modeling

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    3D-Belief maintains and updates explicit 3D beliefs about partially observed environments to enable multi-hypothesis imagination and improved performance on embodied tasks.

  3. The Design and Composition of Structural Causal Decision Processes

    cs.CE 2026-05 unverdicted novelty 7.0 of 10

    SCDMs and SCDPs are composable causal decision models that are strictly more expressive than POMDPs by allowing endogenous memory formation and variable discounting without rational belief assumptions.

  4. MultiWorld: Scalable Multi-Agent Multi-View Video World Models

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.

  5. MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Credit assignment via LMM pairwise comparisons plus Bradley–Terry rank aggregation and potential-based shaping improves cooperative MARL under sparse rewards and dynamic agent counts.

  6. LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    LLawCo extracts misaligned behavioral patterns from agent failures to derive laws, incorporates them via SFT into LLM reasoning, and reports 4.5% and 6.8% success rate gains on PARTNR-Dialog and TDW-MAT benchmarks.

  7. IGen: Scalable Data Generation for Robot Learning from Open-World Images

    cs.RO 2025-12 unverdicted novelty 6.0 of 10

    IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.

  8. VLM4D: Towards Spatiotemporal Awareness in Vision Language Models

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    VLM4D benchmarks spatiotemporal reasoning in VLMs and finds large gaps versus humans, with proposed methods showing partial improvement.

  9. "Harmless to You, Hurtful to Me!": Investigating the Detection of Toxic Languages Grounded in the Perspective of Youth

    cs.CL 2025-08 unverdicted novelty 6.0 of 10

    The authors construct the first Chinese youth-toxicity dataset, show that youth and adult perceptions of toxic language diverge, and report that adding contextual meta information improves detection accuracy.

  10. Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends

    cs.CV 2026-05 unverdicted novelty 2.0 of 10

    This survey reviews trends, challenges, benchmarks, and future directions in action-conditioned interactive world modeling for video and 3D generation.

Pith tools