- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper discusses the problem of emergent misalignment in multi-agent systems, focusing on automated workflows. The authors triy to formally define this problem and behaviour using Bayesian framework. The proposed alignment framework (AEA) uses context specific evidence to improve role adherence by reasoning over agentic traces and priding structured evidence to identify and fix misaligned behavior. Two instantiations of AEA are studied, self-reflection based and weak-to-strong generalization using a small trained evidence model. The results show that evidence-based alignment improves agent collaboration and reliability.
Critical strengths
-
The paper studies an important and timely problem. More and more LLM systems are built as automatically generated multi-agent workflows. When one of these fails, it is often hard to tell which agent went wrong. A single agent that drifts from its role can sink the whole task. The paper’s approach is practical: it pinpoints the agent at fault and repairs only that agent, instead of rerunning or rebuilding the whole system. Attempting a formal treatment of role-specific behavior is also a worthwhile direction, even though it isn’t yet tied to the experiments.
-
The experimental settings are fair in the sense that every fixing method gets exactly one rerun. The Gemma critic sees the same full trace and gives the same kind of output and no method has access to ground truth. Under these rules, AEA-4B beats both retrying and the critic on all 2,500 HLE questions for both strong models. It is also interesting that a small trained 4B critic helps frontier models, while outperforming the same model critiquing.
-
The author also addressed a potential concern: is the gain just from using a different model? The authors train the same Gemma model with their recipe and compare it with the untrained version.
Critical weaknesses
1.The theorems in the paper are standard results, and none of their quantities is measured later in the results. Essentially the theorems describe adding evidence during a decision, while AEA restarts the workflow after reading the whole trace. All the compared critics see the same trace, so the theory can’t explain why they perform differently. Untrained Gemma finds the right agent about as often as AEA-4B, which suggests the gain may come from better output or better prompts rather than from attribution. Therefore the evidence supports a narrower claim than what the paper currently suggests.
-
There is little direct evidence for the role idea. Role adherence is measured in only one workflow, by an LLM judge, with no error bars. The examples in the paper are fixes to math and physics mistakes, not the role failures used as motivation.
-
Statistical robustness of the reported numbers is uncertain. Most benchmarks are tiny (AIME - 30 problems, Physics - 34 problems, Chemistry - 41 problems), so many per-cell differences in Table 1 amount to one or two problems averaged over three seeds.
Questions for authors
- How many tasks per seed are in each table, by my calculation for 3 seeds an average can only take certain values which is not consistent with the current reported numbers.
- How much of the gain comes from naming the right agent? For example, what happens if the new prompt goes to a random agent, or if you count only runs where both critics give valid output?
- Can you compare against AgenTracer, and explain how AEA differs from it and from COPPER?
- Can you add a baseline that uses the same compute as AEA?
4 comments
Response to Reviewer rxoi (Part 2/2)
Q1: Tasks per seed.
- Tasks in each table. Each benchmark uses one fixed task list, as listed below.
| Benchmark | Tasks | Tables |
|---|---|---|
| HumanEval | 164 | 1, 4 |
| DataBench | 257 | 1, 4 |
| Chemistry | 41 | 1, 4 |
| Physics | 34 | 1 |
| AIME24 | 30 | 1, 4 |
| AIME25 | 30 | 1 |
| AIME26 | 30 | 1, 2 |
| HLE | 2,500 | 2 |
| TraceElephant | 85 traces | 14 |
| AIME24/25, two workflows | 120 runs | 16, 17 |
- Attribution counts. The W3 table reports attribution as trace counts, with one count per query for each general-purpose model, and the revised App. K lists them all (Table R3).
Q2: How much of the gain comes from naming the right agent. AEA both names the responsible agent and writes the replacement system prompt for it. It names the responsible agent on 60 of the 85 TraceElephant traces against 59 for the Gemma critic (Table R3). In Table 17, it returns valid evidence in 118 of 120 runs against 103 for the critic, a paired difference of 12.5 points with a 95% CI of [6.7, 19.2]. The revised Sec. 5.5 reports this comparison.
Q3: AgenTracer and COPPER. The revision compares the designs of both methods with AEA in Sec. 2 and App. G (Table R2).
- Comparison with AgenTracer. Both methods attribute a failure to an agent and use the attribution to correct the workflow. AgenTracer trains its tracer on agent and step labels and feeds its reasoning back to failed runs over three further rounds. AEA also writes the replacement system prompt of the identified agent and applies it in a single restart. Table 17 compares AEA with the Gemma critic, which reads the same trace and returns the same schema, since the AgenTracer-8B checkpoint is not public. Under the one-restart protocol, AEA returns valid evidence in 118 of 120 runs. The critic returns it in 103.
- Differences from COPPER. COPPER writes a reflection for every agent from each failed trial and its task reward, over up to five trials. AEA names one agent and needs no task reward, which no method receives in Table 17.
Q4: A baseline with the same compute. The Gemma critic uses about the same compute as AEA, and Naive Retry runs the same restart without an evidence call.
-
The evidence step. The Gemma critic matches the evidence step of AEA. It reads the same trace, returns the same evidence schema and spends about the same number of tokens (433.9K against 430.8K over 120 runs, Table 17), and both methods restart the workflow once. At this matched cost, AEA returns valid evidence in 118 of the 120 runs and the critic in 103.
-
Total compute. Naive Retry matches the cost of the rest of the episode, since it runs the same full restart and makes no evidence call. Beyond this shared restart, AEA adds one evidence call, as the per-task split below shows, with CaptainAgent counted after its shared team-building step.
| Tokens per task | First run | Evidence call | Restart | Total |
|---|---|---|---|---|
| Setting of Table 17 | 21.9K | 3.6K | 22.1K | 47.6K |
| CaptainAgent, GPT-5.5 | 12.7K | 3.1K | 12.1K | 27.9K |
The evidence call takes under 8% of an AEA episode in the setting of Table 17 and about 11% with CaptainAgent and GPT-5.5, and the revised App. E.4 reports these per-task costs.
We hope these answers address your questions, and we would be happy to provide any further clarification.
Dear Reviewer rxoi,
Thank you again for your comments. As the discussion phase ends in one day (November 18), we would like to ask whether our responses have addressed your concerns. If there are any remaining questions, we would be happy to respond.
If you find our responses satisfactory, we would appreciate your consideration in updating the evaluation.
Sincerely,
Authors
Thanks for the clarifications and additional results. However, I am still unclear on how much the gains are due to correct attribution vs better prompts or valid outputs, so i am maintaining my original score.
Response to Reviewer rxoi (Part 1/2)
We thank Reviewer rxoi for recognizing the importance of the problem, the practical design that pinpoints the agent at fault and repairs only that agent, and the fair setting in which every method gets one restart and every critic sees the same trace. We respond to each weakness and each question below.
W1: Theory, restarts and attribution.
AEA returns valid evidence more often in both workflows, and its 12.5-point margin over the critic has a paired 95% CI of [6.7, 19.2]. The revised App. K adds this split as Table R4.
W2: Direct evidence for the role idea.
W3: Statistical robustness. The comparisons we add are paired on the same runs or repeated on the same traces. On the 120 correction runs of Table 17, AEA returns valid evidence 12.5 points more often than the Gemma critic, with a paired 95% CI of [6.7, 19.2]. On TraceElephant, each general-purpose model was queried three times under the protocol of Table 14, and AEA stays ahead of each of them in every query.
AEA and the Gemma critic use greedy decoding.