- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes M²Sim, a macro-micro coupled framework for long-horizon social simulation with LLM-based agents. M²Sim introduces explicit macro-level state distributions and micro-level latent agent states, enabling the simulation of both population dynamics and individual-level evolution. Experiments demonstrate that M²Sim improves over existing baselines in long-horizon simulation and opinion reversal prediction.
Critical strengths
-
The paper addresses an important and challenging problem in LLM-based social simulation. The authors identify the limitation of existing mean-field LLM simulators in capturing long-term opinion dynamics and propose a macro-micro coupled framework to model both population-level evolution and individual-level states.
-
The proposed framework is well motivated. The theoretical analysis provides valuable insights into the failure modes of MF-LLM. By characterizing the self-strengthening behavior of majority states, the paper offers a principled motivation for introducing explicit micro-level states and macro-level dynamics. The experimental results on long-horizon and opinion reversal scenarios demonstrate promising improvements over existing baselines.
Critical weaknesses
Major Weaknesses
-
The experimental comparison is insufficient. The current experiments mainly compare against Direct LLM, Social Retrieval, and MF-LLM, which are relatively outdated baselines. For an ICLR-level paper, the authors should include more recent LLM-based social simulators to better demonstrate the advantages of over existing approaches.
-
The ablation study is too coarse to fully understand the contribution of each component. Finer-grained analysis is needed for key design choices, such as the necessity and effectiveness of the K-step rollout consistency loss.
-
The Policy Model Optimization relies on the state transition model for future trajectory evaluation, but the counterfactual capability of this transition model is not sufficiently validated. assumes that different agent actions can be reliably evaluated through the learned transition model to predict future macro dynamics. However, the experiments do not analyze whether the transition model can accurately capture action-conditioned dynamics or whether policy optimization is affected by potential transition model bias.
-
The Introduction lacks clarity and accessibility. It introduces many domain-specific terms from social simulation, such as variance damping, majority lock-in, and delayed evidence accumulation, which make the motivation difficult to follow even for readers familiar with the field. Moreover, the connection between the limitations of MF-LLM and the design choices of requires a clearer clarification.
Minor Weaknesses
-
The placement of Figure 1 may affect readability. The current framework figure contains many components, including macro dynamics, micro states, and policy optimization. However, readers may not yet understand these concepts when encountering the figure in the Introduction. The authors may consider moving it to the Method section or simplifying the figure.
-
The main paper lacks a dedicated Related Work section.
-
Minor formatting issues: Section 2.3 has an inconsistent title format, with an unnecessary period at the end of the section title. In addition, “MF-MDP” in Figure 2 appears to be the name used in an earlier version of the paper.
Questions for authors
See weaknesses
Learning Mechanism is with Originality
Indeed, this paer has referred MF overall scheme, yet there still exists some novelty in terms of the learning mechanism, which should be acknowledged.
MF only return mean-field dynamics signal before each round of content generation. However, for M^2Sim, the dynamic signal is oriented to the long-term rolling out. That is, we predict the most possible next state from the current mean-field statuts, so as to better process long-term simulation.
MF has not considered individual preference on cognition. In this paper, each agent has been assigend with an individual signal to retain diversity, along with the global macro-signal to target the overall evolving direction. Such the dual-enhacenment is with the most value of this paper compared with the current works.
From prompt to representation. Keeping the transformer model-body, this work maintains the learning on dyanmic-signals at the representation level, which can incorporate more interpretability compared with the prompt-text alone.
In my view, this paper should be further polished: ① modeling on field dynamics. what is the prototype in mathematics ② signal evolving coupled with the multi-agent field evovling. How the guide the evovling direction for agents ③ check on individual diversity. If the injection of macro-signal will erase the individual preference to be over homogeneous.