- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
TACIT relocates multi-agent collaboration from inference-time dialogue to training-time experience transfer. Stage I uses preference optimization to teach agents to append confirmation or uncertainty markers. Stage II constructs agent-specific preference pairs by combining an incorrect or insufficiently confident attempt with a correct, self-confirmed peer trajectory. At inference, selected agents generate independently, optionally revise within the same generation, and contribute to confidence-weighted voting. The manuscript evaluates three backbones on mathematical reasoning and studies learned self-verification and its transfer to code and symbolic reasoning tasks. Tables 1–2 report the highest accuracy in five of eight settings and the second highest in the remaining three. The results are promising, but ambiguities in the implemented method and evaluation protocol, together with incomplete isolation of the gating mechanism, limit the strength of the conclusions.
Critical strengths
- Practical training-time collaboration. TACIT transfers peer experience during training, reducing the need for costly inference-time communication while targeting agents' individual weaknesses.
- Promising empirical results. TACIT achieves the best performance in five of eight settings across three backbones. Self-verification experiments further demonstrate learnable confidence signals and partial cross-domain generalization.
Critical weaknesses
1.Implementation and reproducibility. The router differs between Section 3.4 and Appendix A.2, while Stage II preference construction differs between the main text, Algorithm 2, and code. The relationship between single-generation inference and multi-sample evaluation also remains unclear. 2. Insufficient causal evidence. Table 3 does not isolate confidence gating, since removing Stage I also affects initialization, routing, and voting. Moreover, the claimed efficiency gains lack measured token costs and latency.
Questions for authors
- Can the authors clarify the actual router, preference construction, and evaluation protocols used to obtain the reported results?
- Can the authors isolate the effect of gating while holding other components fixed, and provide measured token costs and latency?
3 comments
> Re W2 & Q2: The claimed efficiency gains lack measured token costs and latency.
We agree that efficiency claims should be supported by explicit computational measurements. To address this concern, we conducted additional evaluations of inference token consumption, end-to-end latency, and throughput across all seven methods on MATH-500 (500 questions) with Qwen3-4B checkpoints trained on MATH. TACIT employs top-3 agent routing without explicit inter-agent communication at inference.
As shown in Table 2, TACIT achieves the highest accuracy (68.28%) while substantially reducing inference costs compared with explicit multi-agent collaboration methods. Specifically, compared with Multi-Agent Debate, TACIT achieves 3.56 percentage points higher accuracy with 58.5% fewer tokens and 43.8% shorter execution time, while improving throughput by 1.78×. Compared with iMAD, TACIT improves accuracy by 2.97 percentage points, reduces token consumption by 21.3% and execution time by 16.9%, and achieves 1.21× higher throughput.
We acknowledge that lightweight single-agent methods incur lower inference costs, but TACIT delivers substantially stronger reasoning performance. These results demonstrate a favorable accuracy–efficiency trade-off, particularly against inference-time multi-agent collaboration, supporting our central motivation: internalizing collaborative experience during training can preserve the benefits of multi-agent reasoning while substantially reducing recurring communication overhead at inference.
Table 2. Inference efficiency comparison on MATH-500 with Qwen3-4B.
| Method | Accuracy (%) ↑ | Total Tokens / Q ↓ | Latency (s) ↓ | Throughput (Q/s) ↑ |
|---|---|---|---|---|
| Chain-of-Thought [1] | 52.40 | 643.718 | 223.428 | 2.238 |
| Self-Consistency [2] | 56.05 | 1281.293 | 246.805 | 2.026 |
| Multi-Agent Debate [3] | 64.72 | 5200.473 | 2032.795 | 0.246 |
| iMAD [4] | 65.31 | 2742.568 | 1375.524 | 0.363 |
| ReVISE [5] | 57.98 | 1231.898 | 868.429 | 0.576 |
| S2R [6] | 63.68 | 1629.767 | 1022.459 | 0.489 |
| TACIT (Ours) | 68.28 | 2157.842 | 1142.573 | 0.438 |
[1] Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc V. Le, and Denny Zhou. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems, 2022.
[2] Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdh- ery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. In International Conference on Learning Representations, 2023.
[3] Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, and Igor Mordatch. Improving factuality and reasoning in language models through multiagent debate. In International Conference on Machine Learning, 2024.
[4] Wei Fan, JinYi Yoon, and Bo Ji. imad: intelligent multi-agent debate for efficient and accurate llm inference. In Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, pp. 29403–29411. AAAI Press, 2026. ISBN 978-1-57735-906-7.
[5] Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim, Jinwoo Shin, and Jihoon Tack. Revise: Learning to refine at test-time via intrinsic self-verification. In International Conference on Machine Learning, pp. 33616–33634. PMLR, 2025.
[6] Ruotian Ma, Peisong Wang, Cheng Liu, Xingyan Liu, Jiaqi Chen, Bang Zhang, Xin Zhou, Nan Du, and Jia Li. S2r: Teaching llms to self-verify and self-correct via reinforcement learning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 22632–22654, 2025.
> Re W2 & Q2: Gating isolation.
We thank the reviewer for this insightful observation. We clarify that the original Table 3 presents a stage-level factorial ablation, intended to assess the contributions of both training stages to the overall framework, rather than isolate the effect of confidence gating alone. We agree that removing Stage I also affects policy initialization and downstream routing and aggregation, making a more fine-grained analysis necessary.
To address this concern, we conducted an additional controlled gating ablation on MATH-500 with Qwen3-4B. Specifically, we use identical Stage I checkpoints and vary only the Stage II training sample selection strategy (with vs. without confidence gating), while keeping the remaining training configurations fixed. We further evaluate both variants under two identical inference settings: (i) uniform routing with majority voting and (ii) competence-based routing with confidence-weighted voting.
| Configuration | Uniform Routing + Majority Voting | Competence Routing + Confidence-Weighted Voting |
|---|---|---|
| No Gating | 64.13 | 65.95 |
| Confidence Gating | 65.74 | 68.28 |
The results consistently demonstrate the effectiveness of confidence-guided transfer. Confidence gating improves accuracy by 1.61 percentage points under uniform routing and by 2.33 percentage points under competence-based routing, confirming its contribution independently of Stage I initialization and the choice of inference aggregation strategy.
Importantly, confidence gating also achieves a 13.8% training acceleration, demonstrating benefits beyond task accuracy. These findings support our central hypothesis that learned self-verification signals help identify more valuable transfer opportunities, enabling agents to focus on informative peer experiences rather than applying supervision indiscriminately.
Overall, this controlled ablation provides more direct evidence that self-verification is not merely an auxiliary capability, but an effective mechanism for improving both the effectiveness and efficiency of cross-agent experience transfer.
We apologize for the delayed response, as we have devoted time to conducting the suggested experiments as thoroughly as possible within the available period and computing resources.
> Re W1 & Q1: Implementation and reproducibility.We thank the reviewer for highlighting these implementation ambiguities. We have clarified the following details to ensure consistency between the methodology, pseudocode, and experimental configuration.
The router is implemented as multi-label classification, consistent with Section 3.4. Each agent receives an independent binary competence label, and the router is trained using binary cross-entropy, allowing multiple agents to be competent on the same question. The multi-class descriptions in Appendix A.2 and Algorithm 2 were inadvertent documentation errors. We have corrected the corresponding label construction, loss function, and pseudocode to accurately reflect the intended implementation.
Section 3.3 specifies two distinct cases:
Algorithm 2 inadvertently omitted this conditional distinction, causing an inconsistency with Section 3.3. We have corrected the pseudocode to explicitly distinguish these two cases and ensure consistency with the actual preference construction.
These refer to different levels of the evaluation procedure. At inference, TACIT routes each question to the top-3 agents among five, with each selected agent independently generating one response per system invocation, followed by confidence-weighted aggregation. No inter-agent communication occurs. In contrast, multi-sample evaluation refers to generating multiple independent samples for benchmark-level performance estimation or sampling-based baselines, rather than additional communication rounds within a single TACIT invocation.
We have clarified the benchmark-specific evaluation settings in the Appendix, including model-specific tokenizer chat templates, prompting, decoding parameters, generation budgets, and answer-verification procedures. Native thinking mode is disabled unless otherwise specified.
We perform zero-shot chain-of-thought evaluation using the backbone’s chat template. GSM8K and MATH-500 use a maximum generation length of 2,048, both pass@1 and majority-vote (self-consistency) accuracy over eight trajectories are recorded. AIME 2024 and AIME 2025 use the same sampling parameters with a maximum of 6144 new tokens and 32 trajectories per problem. MBPP and BBH are evaluated greedily with one trajectory and a maximum length of 2,048. We report execution-based pass@1 for MBPP and macro-averaged accuracy across BBH subtasks.
Table 1. Task Evaluation Configurations.