- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper introduces a unified vision-language Stochastic routing framework (VL-Scout) for efficient multi-Modal and multi-step reasoning with turn-based reinforcement fusion with three unique features. After GRPO, the proposed model enables adaptive computation depth and selective model composition conditioned on reasoning quality. Evaluated on four representative multi-modal benchmarks (MMMU, MMMU-Pro, OKVQA, and RealWorldQA), and compared against 11 representative routing and policy optimization baselines demonstrate the superiority of VL-Scout.
Critical strengths
- The approach is novel, the paper is motivated to minimize the loss by finding the parameters θand ϕthat parametrize the routing and fusion function.
- After GRPO, the proposed model enables adaptive computation depth and selective model composition conditioned on reasoning quality is very interesting.
- Evaluated on four representative multi-modal benchmarks (MMMU, MMMU-Pro, OKVQA, and RealWorldQA), and compared against 11 representative routing and policy optimization baselines demonstrate the superiority of VL-Scout.
Critical weaknesses
- The writing is very unclear and hard to understand the paper.
- The evaluated benchmarks are limited, only 4 benchmarks are demonstrated.
- The performance gap to oracle is still huge.
- The tested models are very old, does this method generalization to new and bigger models?
Questions for authors
see above.
2 comments
Thank the authors for their feedback. Adding one more HallusionBench evaluation is good, but I don't think one more enough is for this general multimodal reasoning approach as multimodal reasoning benchmarks are very abundant. Therefore I maintain the score.
Thank you for the review. We answer each point with new experiments.
First, a clarification about the "superiority" you noted. Table 1 reports GRPO as pass@4, so a query counts as solved if any of several sampled rollouts is correct. We re-ran all experiments scoring one greedy answer given before the label is seen. Under that scoring, VL-Scout is 0.3–0.8 points above the best single model on MMMU, MMMU-Pro and RealWorldQA, and 1.2 below it on A-OKVQA, using fewer calls than voting (details in our reply to qAyi). We revise the claim accordingly.
W4: newer and larger models. We added Qwen3-VL-32B and InternVL3.5-38B (4–5× larger than the original models) and re-ran routing on the resulting 9-model pool (online, top-1, 10 seeds):
The router exploits the new models (+11 points on MMMU over the old pool). It beats TS-MA on three of four benchmarks and has far lower variance than REINFORCE. It needs an up-to-date operator prior, though. A stale prior that ignores the new models anchors exploration (MMMU 57.13), and we now state this limitation.
Fusion also benefits. We use the frozen fusion policy, with the three candidates chosen on the cross-domain source benchmark, so no target labels are used:
Pooled over 2,715 queries, fusion is +1.3 points above the best single model chosen in hindsight (McNemar p = 0.036).
W2: more benchmarks. We added HallusionBench (951 yes/no questions on charts, tables, OCR, maps and visual illusions), using a 6-model open-weight pool:
Fusion beats voting by +7.0 points with half the calls (McNemar p < 0.0001), and with good candidates it matches the best single model (+0.84, not significant).
W3: gap to the oracle. The oracle is a theoretical upper bound. It queries all 7 models on every input and then picks a correct answer whenever one exists. The gap is large because many queries are solved by only one or two models (% of queries by number of correct models):
On MMMU and MMMU-Pro, 29% and 33% of queries are solved by at most two models. On A-OKVQA only 5% are, and 62% are solved by all seven, which is why its gap is small. A system can recover such answers only if it happens to query the one or two models that hold them. That is possible only by calling every model, which defeats the purpose of routing. VL-Scout instead samples at most k (lets say k=3) models per query. When a single model solves a query, a random set of 3 contains it only 3/7 = 43% of the time. The bound that matches our budget is therefore any of the 3 consulted models (3 seeds):
Limiting calls to 3 lowers the bound by 9–12 points on MMMU, MMMU-Pro and RWQA. The router's selections contain a correct model more often than random ones on MMMU and MMMU-Pro (+2.6 / +4.9). We keep the any-of-7 oracle as the theoretical bound and add the budget-matched bound next to it. Within the budget, the remaining headroom is ordering the candidates: with the fusion policy fixed, the oracle order is 5–15 points above random order.
W1: writing. We restructure Sections 3–4 around an algorithm box for the full online loop, a protocol box (predict → score → update), a notation table and an early figure. The figure separates routing (which models, in what order) from fusion (when to stop, what to answer).