- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces BeliefMerge, a novel Bayesian game-theoretic framework for model merging that coordinates task-specific models by framing them as players with private information. The method constructs correlated joint beliefs via a shared latent variable, allowing models to reason about each other's characteristics, and determines contribution weights through a Bayesian Nash Equilibrium (BNE). Supported by theoretical guarantees for equilibrium uniqueness and convergence, the approach achieves state-of-the-art empirical performance across numerous CLIP and GLUE benchmarks, consistently outperforming strong baselines.
Critical strengths
-
The paper innovatively reframes model merging as a Bayesian game with asymmetric information rather than a standard centralized optimization problem. By modeling strategic uncertainty via correlated joint beliefs and coordinating through BNE, it provides a principled, theoretically grounded framework (backed by uniqueness and convergence proofs) for handling incomplete information during merging.
-
BeliefMerge achieves state-of-the-art results across diverse settings, with performance gains scaling favorably alongside task diversity. Furthermore, comprehensive ablation studies effectively validate key design choices—proving that elements like task-vector directions, posterior updating, and Nash coordination all provide genuine, independent benefits beyond simple Bayesian weighting.
Critical weaknesses
-
Insufficient justification for game-theoretic modeling. The paper does not adequately explain why model merging should be treated as a strategic game with artificial information asymmetry rather than a standard centralized Bayesian optimization problem. To prove this elegant formalization is practically necessary rather than just decorative, the authors must compare the BNE approach against a centralized optimizer with the same information structure, or demonstrate specific scenarios (e.g., conflicting objectives) where strategic coordination fundamentally outperforms centralized optimization.
-
Limited analysis of when and why the approach succeeds. The paper lacks a deep investigation into the underlying conditions that make BeliefMerge advantageous over simpler alternatives. Specifically, it is missing critical analyses regarding belief calibration quality (the accuracy of inferred beliefs vs. ground truth and the impact of miscalibration), sensitivity to the correlation structure (when and how much correlation is needed compared to independent beliefs), and the characterization of task compatibility that dictates when strategic coordination is truly beneficial.
Questions for authors
1.Could you provide an ablation comparing your BNE-based approach against a centralized Bayesian optimizer that directly optimizes joint utility with full access to all private information, to justify the practical necessity of the game-theoretic view?
2.How sensitive is the method to belief miscalibration; specifically, what is the actual accuracy of inferred beliefs versus ground truth, how does performance degrade with deliberately perturbed priors, and in what exact scenarios do correlated beliefs outperform independent ones?
3.How many strategy optimization iterations are typically needed for convergence, what is the minimum calibration set size required, and when should practitioners prefer BeliefMerge over computationally cheaper baselines?
7 comments
Response 2 to Reviewer iMM8
Weaknesses 2/Question 2:Limited analysis of when and why the approach succeeds...
We thank the reviewer for these valuable suggestions. Regarding belief calibration quality, we compare inferred private information with ground-truth statistics computed from each model’s local data. In Fig. 7, RMSE decreases from 0.57 at 2 steps to 0.06 at 2,048 steps. Meanwhile, merging accuracy reaches 89.2% at 512 steps and remains stable through 2,048 steps. These trends are consistent with more accurate private information estimates supporting contribution coordination and sustained merging performance.
Regarding sensitivity to the correlation structure, the Independent Beliefs (IB) variant in Fig. 5 replaces the joint belief with the product of its conditional marginals, removing cross-model dependence while preserving the conditional marginal distributions. This reduces accuracy by 1.2 and 1.4 percentage points on ViT-B/32 and ViT-B/16, respectively, supporting the benefit of modeling dependence beyond marginal information in the evaluated settings. And regarding strategic coordination across tasks, w/o NO in Fig. 6 replaces individual best responses with centralized maximization of average expected utility while retaining the joint beliefs, utility functions, and merging rule. The accuracy decreases by 2.2 and 1.9 percentage points on ViT-B/32 and ViT-B/16, respectively, supporting the practical benefit of Nash coordination.
To further examine when correlated beliefs and Nash coordination are beneficial, we evaluate three eight-task subsets from the 20-task CLIP benchmark on ViT-B/32. Using the average directional similarity in Eq. (27), we select subsets closest to the 10th, 50th, and 90th percentiles, representing low, medium, and high similarity, respectively. We compare full BeliefMerge with two existing variants: IB (Fig. 5), which replaces the joint belief in Eq. (10) with the product of its conditional marginals, and w/o NO (Fig. 6), which replaces individual best responses in Eq. (16) with centralized maximization of average expected utility. These comparisons assess how the benefits of correlated beliefs and Nash coordination vary across task combinations. Table B shows that gains from correlated beliefs and Nash coordination decrease from 1.5 to 0.9 and from 2.8 to 1.3 percentage points as task-vector similarity increases, suggesting greater benefits for less directionally similar task combinations in the evaluated subsets. We have added these comparisons and the corresponding experimental details to Section 4.3.
Table B. Benefits of correlated beliefs and Nash coordination across task combinations. Low, Medium, and High denote the three eight-task subsets.
| Subset | IB | w/oNO | BeliefMerge |
|---|---|---|---|
| Low | 87.6 | 86.3 | 89.1 |
| Medium | 87.7 | 87.2 | 88.9 |
| High | 87.9 | 87.5 | 88.8 |
Question 3: How many strategy optimization iterations are typically needed for convergence...
We thank the reviewer for these valuable suggestions. We do not require an additional independent calibration dataset: the belief model learns from existing public information and local statistics during training Appendix D.3. Our training directly optimizes the contribution strategies. Fig. 7 shows that merging accuracy reaches 89.2% at the 512-step task-model fine-tuning checkpoint and remains stable through 2,048 steps.
Regarding practical use, Table 7 reports a merging time of 50.14 seconds on the eight-task CLIP ViT-B/32 benchmark, compared with 40.64 seconds for TSV-M (Gargiulo et al., 2025) and 62.92 seconds for Iso-CTS (Marczak et al., 2025), which represent subspace-based merging. BeliefMerge requires only 1.81 seconds more than the strongest overall baseline (Crisostomi et al., 2026), which represents input-dependent merging, while using 29.0% less peak memory. BeliefMerge uses 4.45 GB of peak memory, compared with 3.59–3.92 GB for Task Arithmetic, TSV-M, and Iso-CTS. Specifically, Task Arithmetic (Ilharco et al., 2023), representing simple parameter arithmetic, takes only 0.08 seconds, but its accuracy is 68.8% compared with BeliefMerge 89.2% under the same benchmark setting—a gap of 20.4 percentage points (Table 1). We therefore recommend BeliefMerge when merging quality is a priority and local task statistics are available; Task Arithmetic may be preferable when merging time is more important than accuracy.
Thank you & Looking forward to further discussion!
Dear Reviewer iMM8,
Thank you again for your constructive review. We briefly summarize our key clarifications and additional evidence:
-
Practical Benefits of Game-Theoretic Modeling (
Weakness 1;Question 1): BeliefMerge forms correlated joint beliefs about other models’ unobserved private information and coordinates interdependent contributions through conditional expected utilities. InFig. 6,w/o NOreplaces individual best responses with centralized average expected-utility maximization while retaining the information structure, beliefs, utilities, and merging rule. Furthermore,Table Acompares BeliefMerge with Centralized BO using all models’ true private statistics. Both comparisons support the practical benefit of Nash coordination. -
Belief Estimation and Task Compatibility (
Weakness 2;Question 2):Fig. 7shows decreasing private-statistic estimation error alongside sustained merging accuracy. Independent Beliefs inFig. 5removes cross-model dependence while preserving conditional marginals, andw/o NOisolates Nash coordination. Furthermore,Table Bcompares these variants across task subsets with different directional similarities, showing greater benefits from correlated beliefs and Nash coordination for less similar combinations within the evaluated subsets. -
Efficiency and Practical Use (
Question 3):Table 10inAppendix Fshows modest additional merging time and lower peak memory than the strongest overall baseline. Task Arithmetic is faster but achieves lower merging accuracy (Table 1). These comparisons support BeliefMerge when merging quality is the priority and local task statistics are available, while Task Arithmetic may be preferable when merging time matters more.
We appreciate your valuable suggestions and look forward to further discussion.
Warm regards,
Authors
Response 1 to Reviewer iMM8
We appreciate your thoughtful review and constructive suggestions. We have carefully considered your feedback and provide the following clarifications to address your concerns.
We thank the reviewer for highlighting the need to clarify the motivation and practical benefits of our game-theoretic modeling. BMM (Li et al., 2026a) uses a merged model obtained by methods such as TA (Ilharco et al., 2023) or TSV (Gargiulo et al., 2025) as a prior and estimates merged parameters through Bayesian regression using task-specific activations and residual outputs. It then uses Bayesian optimization to jointly tune module-specific hyperparameters based on average validation performance. Since task-specific models share the same pretrained base, their private information may be statistically dependent. Differences in task data and training further introduce uncertainty about other models private information and contributions. BMM does not explicitly model how other models unobserved private information affects their contributions and, in turn, a model own contribution decisions. BeliefMerge addresses this gap by forming joint beliefs about other models private information, propagating this uncertainty through their contribution strategies to distributions over actions, and coordinating interdependent contributions through conditional expected utilities.
Fig. 6includesw/o NO, a centralized expected-utility optimizer with the same information structure as BeliefMerge. Each contribution strategy remains bm=σm(sm,o), as inEq. (11). This variant retains the joint beliefs, utilities, and merging rule, but replaces the individual best responses inEq. (16)with centralized maximization of the average expected utility, maxσEs∼π(⋅∣o). On the 20-task CLIP benchmark, accuracy decreases from 86.4% and 86.9% to 84.2% and 85.0% on ViT-B/32 and ViT-B/16, respectively, corresponding to drops of 2.2 and 1.9 percentage points. These results support the practical benefit of Nash coordination over centralized average expected utility maximization under the same information structure.To further address the reviewer suggestion, we add Centralized BO as a centralized Bayesian optimization baseline that directly maximizes joint utility with full access to all models private information. Specifically, we compute the true private statistics sm⋆ from each model local data using
Eqs. (5)–(7)and provide them to the optimizer. We replaceEq. (16)with centralized joint utility maximization, b⋆=bargmaxM1∑m=1Mum(b;sm⋆,o).Table A. Comparison of centralized joint utility optimization with full information access and BeliefMerge.
Table Ashows that, compared with Centralized BO, BeliefMerge further improves accuracy by 1.3 and 1.1 percentage points on ViT-B/32 and ViT-B/16, respectively. These results show that coordinating contributions through individual best responses yields higher merging accuracy than centralized average utility maximization, providing empirical support for the game-theoretic formulation. We have added these comparisons and the corresponding experimental details toSection 4.3.