- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces Diagnostic Consensus Energy Minimization (D-CEM), a framework for controlling discussions between two agents in high-stakes classification tasks. It uses historical confusion matrices and asymmetric error costs to identify dangerous alternative diagnoses and decide when agents should continue discussing, reconsider their predictions, make a decision, or escalate. Experiments on synthetic and clinical datasets show that D-CEM can reduce harmful consensus and high-risk errors while improving the trade-off between decision quality and deliberation cost.
Critical strengths
Risk-aware approach to multi-agent deliberation: The paper addresses an important problem where agents can agree on an incorrect decision despite appearing confident. Using historical confusion patterns and asymmetric losses to guide targeted challenges, stopping, and escalation is a meaningful improvement over relying on consensus alone.
Strong experimental and theoretical support: The paper combines theoretical risk analysis with experiments on synthetic and clinical datasets, including comparisons against aggregation and selective-prediction baselines. The additional studies of steering compliance, confusion-matrix quality, and escalation help explain which components contribute to the observed improvements.
Critical weaknesses
Reliance on historical confusion matrices: D-CEM uses fixed confusion matrices to estimate risk throughout deliberation, even though agent behavior may change after targeted challenges or repeated interaction. While the paper includes robustness experiments, it remains unclear how reliably these estimates reflect actual risk when model behavior or error patterns shift substantially.
Sensitivity to escalation costs and limited clinical generalization: Some safety improvements depend on escalating uncertain cases, and the assumed cost of escalation affects whether this is beneficial. For example, Appendix I.3 shows that on DDXPlus, the full method has higher total cost than its no-escalation variant at the paper's chosen unit escalation cost, while the clinical experiments themselves are limited to controlled tasks and two LLM backbones
Questions for authors
How sensitive is D-CEM to changes in agents' confusion patterns during multi-round discussions, particularly when targeted challenges change their predictions? Could the authors evaluate whether updating or recalibrating these estimates improves the reliability of the controller?
How should escalation costs be selected in realistic applications, and under what conditions does escalation improve overall decision quality enough to justify its cost? Additional analysis would help clarify when the full protocol is preferable to simpler stopping or rejection strategies.
3 comments
Response to Reviewer iJEZ (2/2)
W2-1 & Q2. How should the escalation cost be chosen, and when is escalation worth it?
The escalation cost is deployment-specific: each hospital can set it according to its own workflow and safety priorities, and whether escalation pays off depends on this choice. Specifically:
- How to choose the cost.
We use only as a reference point: under the DDXPlus loss (0 correct, 1 ordinary error, 5 high-risk miss), it counts one escalation as one ordinary error. In deployment, hospitals can set their own value from the cost of a specialist review relative to the harm of a misdiagnosis [1]. If this is hard to state, they can instead pick the operating point on the CAL risk–coverage curve that meets their referral budget or safety ceiling [2].
- When escalation is worth it.
Given this cost, escalation lowers risk but pays for each referral. As a result, full D-CEM has lower total cost than D-CEM without escalation whenever is below the break-even value , where and are the system risks with and without escalation and is the escalation rate (Appendix I.3, Figure 6). For instance:
- MedQA-Tri (): escalation already pays off at (0.640 vs. 0.648).
- DDXPlus (), the example you mention: at , full D-CEM costs slightly more (0.341 vs. 0.286) but cuts autonomous system risk by about 72%; at , it is also cheaper (0.211 vs. 0.286).
In short, escalation is worth it when specialist review is cheap relative to misdiagnosis harm (as on MedQA-Tri, or on DDXPlus at ), or when a hospital prioritizes safety over a small cost increase (as on DDXPlus at ). Moreover, whenever a hospital does escalate, D-CEM is cheaper than a simpler rejection strategy: at the same 26% escalation rate on DDXPlus, it costs 0.048 less than Static-CM-ER for every (Appendix I.3).
In our revised manuscript, Appendix E explains how to choose in practice, complementing the break-even analysis in Appendix I.3 (Figure 6).
[1] Mozannar & Sontag, "Consistent Estimators for Learning to Defer to an Expert," ICML 2020.
[2] Geifman & El-Yaniv, "SelectiveNet: A Deep Neural Network with an Integrated Reject Option," ICML 2019.
W2-2. Generalization beyond controlled tasks and two LLM backbones
The controlled scenarios (S1–S3b) are a test design, not a requirement of D-CEM: we use them to isolate premature diagnostic closure under asymmetric expertise, complementary errors, and shared bias. D-CEM itself treats agents as black boxes and supports multi-agent pooling (Appendix B.7), so new backbones or larger panels keep the same control logic and only require recalibrating and the thresholds on CAL (Appendix K).
Empirically, two sets of results in Appendix I.4 support this. First, Table 16 (original submission) removes all role anchors on DDXPlus under neutral prompts and expands the label space to ; D-CEM achieves the lowest and the lowest or tied-lowest H.C. at every . Second, as a new experiment, we add a third backbone (Llama-3.2-3B paired with gpt-4o-mini) in the same setting with enlarged test splits (Table 17); D-CEM again achieves the lowest H.C. and at every , both at 0% escalation and at matched escalation.
In our revised manuscript, Appendix I.4 reports the neutral-prompt results (Table 16) and the new third-backbone results (Table 17).
Looking forward to further discussion
Dear Reviewer iJEZ,
We sincerely thank you again for your thoughtful review. As the discussion deadline approaches, we wanted to gently follow up. If time permits, we would be very grateful to know whether our responses have addressed your concerns or whether you have any remaining questions. Thank you again for your time and thoughtful review.
Best regards,
Authors
Response to Reviewer iJEZ (1/2)
Thank you very much for your careful review and for recognizing the importance of the problem, our risk-aware deliberation approach, and our theoretical and experimental support. We directly address each of your concerns and questions below.
Fixed confusion matrices (CMs) remain reliable across discussion rounds, even after targeted challenges change the agents' predictions, and recalibrating them brings only a small efficiency gain.
We hold the CMs fixed because the mediator cannot access the true label of the current case, so a pre-deployment offline estimate from historical data (CAL, 70–80 labeled cases) is a practical approach. Our work focuses on short-term deliberation; for longer-term use, periodic recalibration between deployment windows can be applied. Within this scope, we add two new experiments.
Experiment 1: do fixed CMs still match agent behavior after steering? Using DDXPlus ground-truth labels, we check fixed-CM posteriors and predicted risks against observed outcomes, both across rounds and for the same agent on the same case just before vs. after
DIFFERENTIAL_STEER(n is the number of agent-round reports; all metrics are group means).Takeaway: steering does not widen the gap between fixed-CM and empirical posteriors (TV 0.122 → 0.120). Moreover, predicted risk exceeds observed loss in rounds 1–3 and at certified stops, i.e., the estimates are conservative where decisions are made; slight underestimation appears only in unresolved hard cases (rounds 4–6), which escalation covers. Targeted challenges therefore do not break the fixed-CM risk estimates.
Experiment 2: does recalibrating the CMs make the controller more reliable? We then run the complete DDXPlus controller with three CM choices, all fitted on CAL: fixed Ca, separate pre-/post-steer CMs, and round-specific CMs.
Takeaway: safety is similar across all three (H.C. 1.20% vs. 1.09%/1.15%), while recalibrated CMs only modestly lower escalation (44.2% → 41.8%) and total cost. However, they need multi-round deliberation on CAL and split its 70–80 cases across rounds or intervention states, which is a substantial offline overhead. Fixed Ca is therefore a lightweight default with similar observed safety.
Moreover, safety is preserved even under much larger CM errors: when each CM is mixed with a uniform matrix, Cη=(1−η)C+ηU, H.C. stays at 0.4% even at η=0.5, and only the total cost rises (main DDXPlus setting: 0.341 → 0.445; Appendix I.5, Table 20).
In our revised manuscript, Section 2.2 clarifies how the CMs are estimated and states the short-term scope, and Appendix I.2 reports both analyses (Tables 13 and 14).