- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
Multi-agent workflows spend different amounts of computation on different queries. The paper routes each query through three dependent decisions, the collaboration topology, the number of agent positions, and the language model at each position. A frozen sentence encoder feeds small trainable heads, and retrieved records of past executions bias the routing distributions. All decisions are trained with a policy gradient under one reward that subtracts inference cost from task performance. On four benchmarks the method is compared with routing and workflow baselines on accuracy and training cost.
Critical strengths
- The three decisions are trained under one execution level reward instead of per stage proxies. The ablation includes a shuffled assignment control that keeps model composition and breaks placement. That is the right test of whether positions matter.
Critical weaknesses
-
The paper never defines what a node does. There is no prompt template per position, no edge payload specification, and no definition of the aggregation step, including whether it is a model call counted in the reward cost. Every number depends on these choices.
-
The ablation undercuts the headline dimension. Random topology sampling scores within about half a point of learned routing on MATH at lower cost. Fixed topologies span roughly one point, and no table carries seeds or confidence intervals.
-
The learned behavior is mostly benchmark level. One backbone receives about four fifths of positions on MMLU and under four percent elsewhere. The memory retrieves only same domain records, so most behavior is reproducible by a per benchmark lookup. The subfield association in Figure 9 has no per cell counts, and the null difficulty result is equally consistent with a router that does not track difficulty.
Questions for authors
-
Specify the per position prompt, the edge content, and the aggregation step. Is aggregation a model call, which model runs it, and does it count inside the cost term.
-
With five seeds and intervals on the main and ablation tables, does learned topology routing beat random topology sampling on MATH, and does the method stay above MasRouter on MATH.
-
What happens when every position is fixed to each of the other three backbones. The current fixed assignment arm uses only one backbone, and not the strongest one on the two benchmarks where it is reported (Table 1 has gpt-oss-120b above nemotron-3-ultra on MATH and MBPP), so it conflates placement with model choice.
-
What are the test set sizes and the per token prices behind the cost axis, and what does the router itself cost per query next to a routed single call.