- Rating
- 4
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies the problem of continuous collaboration in embodied multi-agent systems. It introduces the Tapestry Benchmark to evaluate the ability of embodied multi-agent systems to accumulate, share, and reuse historical information across multiple continuous and interdependent episodes. The benchmark constructs cross-episode dependencies among entities, states, and configurations through evolving environments, and further incorporates robustness challenges including instance ambiguity, historical evidence interference, and infeasible constraints. The authors also propose Tapestry Reasoning, which consists of Tapestry Weaving and Tapestry Evidence Grounding. The former organizes historical information across agents and episodes, while the latter retrieves and leverages relevant evidence to perform history grounding for current tasks.
Critical strengths
- This paper investigates a continuous multi-agent embodied collaboration problem that is clearly meaningful yet remains underexplored, and provides a relatively comprehensive benchmark for its evaluation.
- The experimental analysis is comprehensive, with in-depth diagnostics of historical reasoning and multi-agent collaboration.
Critical weaknesses
- Fig. 2 could be redrawn or further refined, as the current presentation appears somewhat cluttered. In addition, some of the text is too small, and the font styles are not fully consistent. Other figures and tables could also benefit from further optimization.
- If possible, I suggest including a few simple but more informative baselines, such as a Long-Context baseline that directly feeds the entire interaction history into the model, and a Flat Retrieval baseline based on BM25 or embedding similarity under the same history and context budget.
Questions for authors
- The experiments on 3DSPMR, FindingDory, and MEMENTO in the appendix are important for understanding the effectiveness of the proposed method. In the final version, I suggest moving these results to the main paper.