- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper addresses the accuracy–cost trade-off in LLM-based multi-agent collaboration by learning when and with whom agents should communicate. It proposes ACTS, a communication topology scheduling framework that keeps the underlying LLMs frozen and follows centralized training with decentralized execution. Local controllers select communication modes, while role-aware relational attention guides partner selection to form adaptive directed communication graphs. A topology-aware value mixing mechanism enables joint training of these decisions under an objective balancing task accuracy and token cost. Experiments across nine benchmarks with two LLM backbones report improved accuracy and communication efficiency over the evaluated multi-agent baselines.
Critical strengths
I appreciate the paper’s contribution toward learning adaptive communication topologies for LLM-based multi-agent collaboration. The main text and appendix together provide a largely comprehensive and clear description of the method. Most methodological details, including topology construction, value mixing, and the training and execution procedures, are explained explicitly, making the overall framework easy to follow and assess.
Critical weaknesses
1.The evaluation is restricted to three-agent teams, providing limited structural complexity for a method centered on communication topology optimization. With at most two candidate partners per agent, this setting offers limited scope to assess partner selection and the claimed benefits of variable-cardinality routing. Experiments with larger teams are needed to establish whether the accuracy and efficiency gains persist as the communication structure becomes more complex.
2.The authors describe relational attention as selecting communication partners based on semantic relevance. However, learned attention scores alone do not establish this interpretation, and the observation specification in Appendix E.2 does not clarify how message content enters the controller. The authors should explain how generated and received messages are encoded into to support semantic relevance-based partner selection.
3.Topology-aware value mixing is a key contribution of the paper. However, the proposed module differs from QMIX in both its use of explicit topology information and its attention-based mixing architecture. Replacing the entire module with QMIX does not isolate these contributions, making it unclear whether the gains stem from topology information or the architectural change. An additional ablation retaining the attention-based mixer while removing explicit topology features would clarify this distinction.
Questions for authors
1.Although ACTS reduces token consumption, according to Equations (4)–(5) relational attention requires each agent to access representations from all other agents. Does this introduce additional communication and computational overhead that is not captured by the token-based cost metric? How does this overhead scale with the number of agents, and how might it affect the overall efficiency gains in larger teams?
2.The motivation contrasts ACTS with centralized methods that generate a topology before execution. However, I think a centralized controller could also update the topology at each communication round. If the same agent information is available to a centralized controller, what motivates the choice of decentralized decision-making in ACTS, and what advantages or trade-offs do the authors see relative to centralized control?
4 comments
Response to Reviewer rz8J — Part 2/4: Shared execution and computational overhead (Q1)
Thank you for asking whether token savings translate into practical efficiency once shared attention is included. The analysis distinguishes execution requirements, measured inference latency, and training costs.
Execution requirements. Sections 3.2–3.4 and Appendix D describe a shared orchestrator that computes GNN–GRU control representations and relational attention across agents. Attention scores candidate partners and refines the features used for per-agent mode decisions. Modes and partner scores jointly determine participation and directed communication. The topology-conditioned mixer supplies the cooperative objective during training. The execution network combines the learned agent policy with shared relational attention.
Inference overhead. Pairwise attention scoring costs O(N² d_rel) per round. Appendix E.5.2 (Table 8) reports accumulated per-question latency: controller time (Ctrl.) in ms/question and end-to-end time (E2E) in s/question.
| Backbone | N | Ctrl. ACTS | Ctrl. Agent Q-Mix | E2E ACTS | E2E Agent Q-Mix |
|---|---|---|---|---|---|
| GPT-OSS-120B | 3 | 4.7 | 5.8 | 18.6 | 21.9 |
| GPT-OSS-120B | 6 | 8.4 | 11.8 | 31.7 | 39.8 |
| DeepSeek-V4-Flash | 3 | 4.5 | 5.6 | 16.8 | 20.1 |
| DeepSeek-V4-Flash | 6 | 8.1 | 11.5 | 29.4 | 36.2 |
Controller timing covers observation construction, the GNN–GRU policy and relational attention, action selection, and graph construction. End-to-end timing additionally includes the agent and final-decision LLM calls. For six-agent GPT-OSS, these measurements are 8.4 ms and 31.7 s per question, respectively, versus 39.8 s end-to-end for Agent Q-Mix. ACTS records lower controller and end-to-end latency in all four configurations. Thus, the token advantage is accompanied by lower total inference time with shared computation included.
The measurements describe shared-orchestrator execution. O(N² d_rel) covers pairwise attention. A deployment across separate nodes would additionally incur representation-transfer costs.
Training costs. Table 8 reports input + output training tokens (M = millions), rollout time, and optimization time (h = hours). GPT-OSS and DeepSeek abbreviate the backbones above.
| Backbone | N | Method | Train tokens (M) | Rollout (h) | Optim. (h) |
|---|---|---|---|---|---|
| GPT-OSS | 3 | ACTS | 0.38 | 4.62 | 0.18 |
| GPT-OSS | 3 | Agent Q-Mix | 0.47 | 5.47 | 0.15 |
| GPT-OSS | 6 | ACTS | 0.64 | 7.91 | 0.31 |
| GPT-OSS | 6 | Agent Q-Mix | 0.83 | 9.86 | 0.27 |
| DeepSeek | 3 | ACTS | 0.33 | 4.18 | 0.17 |
| DeepSeek | 3 | Agent Q-Mix | 0.41 | 4.96 | 0.14 |
| DeepSeek | 6 | ACTS | 0.58 | 7.15 | 0.29 |
| DeepSeek | 6 | Agent Q-Mix | 0.74 | 8.92 | 0.25 |
ACTS uses fewer training-interaction tokens and less rollout time in every configuration, with slightly higher optimization time. Together with the inference measurements, these results show that the learned scheduler's interaction savings extend to both training and execution.
Revision locations: Sections 3.2–3.4, Appendix D, and Appendix E.5.2 (Table 8). The execution clarification and cost measurements are highlighted .
Thank you again for helping us connect token efficiency to the computation required in practice.
Best regards,
The authors
Response to Reviewer rz8J — Part 3/4: Message semantics and factorized control (W2, Q2)
Thank you for identifying the ambiguity in semantic partner selection and for distinguishing dynamic topology updates from centralized control. We have clarified both points and connected the architectural choices to controlled experiments.
Scheduler inputs and identity. Observations include a deterministic 32-bit question hash, a 16-dimensional one-hot agent identifier as used in Agent Q-Mix’s public implementation, answer availability, degree information, normalized cumulative token use, and previous activity flags (Sections 3.1–3.2, Appendix E.2). The graph separately enters the GNN, and the GRU summarizes graph-conditioned control history. Identity information has distinct uses:
- Observation identity distinguishes agents with fixed role assignments.
- Role prompts condition LLM calls.
- Learned agent-index embeddings condition the training-only mixer.
Generated and received answers supply the LLM language contexts after routing. The shared orchestrator computes each agent's recurrent representation from task and identity features, execution statistics, and the current graph. Pairwise attention scores these control states, expressing control-state-conditioned partner preferences, rather than semantic agreement or relevance between answer texts. Figure 4 (p.6) makes the distinction visible: training is on the left, scheduling in the middle, and answer generation and aggregation on the right. Scheduler parameters stay fixed at inference while control states and graphs evolve.
Controlled evidence. Table 2 evaluates the following interventions within ACTS. ACC is nine-benchmark macro accuracy (%), and tokens are thousands per question.
| Configuration | GPT-OSS ACC | Tokens | DeepSeek ACC | Tokens |
|---|---|---|---|---|
| Full ACTS | 75.01 | 5.97 | 69.43 | 4.03 |
| Without observation identity | 73.40 | 6.80 | 67.10 | 4.60 |
| Fixed communication partners | 72.50 | 8.10 | 66.10 | 6.20 |
| ACTS mixer → QMIX | 71.83 | 7.41 | 63.24 | 4.96 |
- Agent identity: removing observation identity retains role prompts and mixer embeddings, isolating this input's contribution.
- Partner selection: fixing partners lowers accuracy and increases tokens on both backbones.
- Team-value learning: replacing only the ACTS mixer with QMIX also worsens both metrics. This controlled ablation retains the ACTS execution network and changes its training mixer.
Rationale for factorized control. We agree that a centralized controller can update its graph every round. ACTS factorizes mode decisions so that each agent selects its highest-valued mode from six scores, while training uses one cooperative team objective. Following QMIX, nonnegative mixing weights ensure that these greedy choices jointly maximize the team value represented by the mixer at fixed pre-decision context (Eq. (12), Appendix C.3). This provides greedy consistency within the represented monotonic value class. Execution still uses shared control representations for relational attention. The controlled comparisons above assess the contributions of identity, partner selection, and value mixing within this architecture.
Revision locations: Sections 2.1, 3.1–3.4 and 4.3.3, Figure 4, Table 2, and Appendices C.3, D, E.2 and E.7. The corresponding clarifications and ablation discussion are highlighted .
Thank you again for helping us clarify how learned topology scheduling supports LLM collaboration.
Best regards,
The authors
Response to Reviewer rz8J — Part 4/4: Isolating explicit neighborhood inputs (W3)
Thank you for identifying that replacing the mixer with QMIX changes both its architecture and its topology inputs. The targeted ablation follows your suggestion to retain the attention architecture. Building on attention-based value mixing as studied in Qatten, it holds the mixer architecture fixed and varies only the directed-neighborhood channels, directly testing the topology-conditioning mechanism.
Targeted intervention. The new variant in Table 2(d) and Appendix E.7 changes only the mixer's explicit neighborhood inputs:
- Zeroed inputs: the
incoming- and outgoing-neighborhood mean aggregatesin Eq. (9). - Retained components: the attention-mixer architecture, learned agent-index embeddings, and execution-network architecture.
- Evaluation procedure: retrain the variant from scratch and evaluate the resulting scheduler.
ACC is nine-benchmark macro accuracy (%). Tokens are thousands per question.
| Mixer configuration | GPT-OSS ACC (%) | GPT-OSS tokens | DeepSeek ACC (%) | DeepSeek tokens |
|---|---|---|---|---|
| Full ACTS | 75.01 | 5.97 | 69.43 | 4.03 |
| Zero incoming/outgoing neighborhood means | 72.67 | 7.40 | 67.11 | 6.72 |
| Change vs. full ACTS | −2.34 pp | +1.43 | −2.32 pp | +2.69 |
Zeroing the neighborhood inputs reduces accuracy by 2.34/2.32 percentage points and increases token use by 1.43/2.69 thousand tokens per question on GPT-OSS/DeepSeek. The consistent direction across backbones supports the contribution of explicit directed-neighborhood conditioning within the same attention architecture. These inputs shape training, and their benefit appears in the accuracy and communication cost of the learned execution policy.
These two channels separately summarize the peers connected to an agent in each direction on the pre-decision graph. Graph propagation and relational partner selection remain available at execution. The intervention therefore isolates these explicit training-time neighborhood inputs within the same attention architecture, connecting topology-conditioned value learning to the resulting policy's coordination performance.
Reporting basis. Table 9 provides benchmark-level correct/total counts for the added variant. Its accuracy is computed from these counts, while full ACTS uses the mean of three independent scheduler-training runs as the reference.
Revision locations: Section 4.3.3, Table 2(a,d), and Appendix E.7 (Table 9). The intervention, results, and discussion are highlighted .
We appreciate this suggestion, which enabled a more direct test of why topology enters the training objective.
Best regards,
The authors
Response to Reviewer rz8J — Part 1/4: Larger teams and partner selection (W1)
Dear Reviewer rz8J,
Thank you for recognizing the contribution of learned communication topologies and for identifying the limitation of a three-agent test. With only two possible peers, partner selection can resemble mode selection. A larger team provides a more informative test of whether learned routing continues to improve coordination.
From three agents to larger teams. In the main three-agent comparison, ACTS gains 3.17/6.19 pp in macro accuracy with 19.43%/18.75% fewer inference tokens than Agent Q-Mix on GPT-OSS-120B/DeepSeek-V4-Flash (Tables 1 and 3). The larger-team evaluation tests whether this joint advantage persists with more candidate communication partners.
Larger-team evaluation. Section 4.3.4 and Appendix E.8 evaluate
N = 6on all nine benchmarks with both backbones, increasing each agent's potential partners from two to five. ACTS and Agent Q-Mix use the same 60-episode training budget and at most five communication rounds.One mode, different partner sets. A six-agent sender still makes the same six-way mode decision. Under
attn-broadcast, it requests a link to each active peer whose attention to the sender exceeds the threshold. Changing these scores changes both the identities and the number of recipients while the mode stays fixed (Section 3.2). This separates learned partner selection from mode selection.The table combines the main N = 3 comparison with the added N = 6 evaluation (Tables 1 and 3). ACC is nine-benchmark macro accuracy (%). Tokens are thousands per question.
The larger-team evaluation yields two consistent improvements:
Participation and connectivity. Table 10 reports 4.11/4.00 active agents and 5.80/5.58 directed edges per executed round for ACTS on GPT-OSS/DeepSeek, compared with 5.19/5.10 agents and 9.69/9.40 edges for Agent Q-Mix. Higher accuracy accompanies more
selective participation and routingwithin the larger team. Edge counts describe connectivity, while the fixed-partner ablation in Table 2(b) tests partner choice more directly: fixing partners lowers accuracy and raises token use on both backbones. Together, these results connect the larger-team advantage to the purpose of learning whom agents should communicate with.The N = 6 results use benchmark-level correct/total counts. The three-training-run statistics in the manuscript describe the native N = 3 setting. Expanding the team increases token use for both methods. Within the larger-team setting, ACTS retains its accuracy and token advantage over Agent Q-Mix.
Revision locations: Section 4.3.4, Table 3, and Appendix E.8 (Table 10). The corresponding results and discussion are highlighted in blue.
Thank you again for encouraging a more informative test of the scheduler's routing choices.
Best regards,
The authors