- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents TRACEAEGIS, a method for finding unusual behavior in an LLM agent's tool-use logs. It learns normal call patterns from past logs and uses an LLM to summarize the conditions associated with those patterns. It then checks whether new logs follow the learned call structure and conditions. The authors test it on simulated clinical triage and procurement tasks with five detector models. It improves F1 over the corresponding direct LLM detectors in both tasks. In a separate, authorized internal red-team test, it detects 132 of 140 deliberately created abnormal paths.
Critical strengths
-
The idea is easy to understand and addresses a useful problem. A tool call can be wrong because it happens in the wrong order or because its content does not fit the task. The method checks both, using tool-use logs without needing the agent's internal reasoning.
-
The reported gains appear across five detector models and both benchmark tasks. Removing either the structural or semantic component reduces performance in the reported clinical-triage tests. The authors provide the data-generation process and rule prompts. They also clearly state that the clinical tasks are simulated and that the internal security tests were authorized.
Critical weaknesses
-
The comparison does not show how the method performs against other tools designed for this problem. Table 2 compares TRACEAEGIS with direct LLM detectors, while Section 5 discusses other methods that analyze execution logs or tool dependencies. Without comparisons with suitable examples of those methods, it is difficult to judge how much the new design adds. The baseline's access to historical normal logs should also be made clear.
-
The benchmark covers two fixed workflows. This is useful evidence for those tasks, but five detector models do not mean five different types of agent workflow. Section 4.1 states that the profiling and test logs are separate. It is less clear whether they also use different task templates and request patterns. Table 1 shows different average path lengths across normal and abnormal examples, which is worth checking with a simple comparison based on length.
-
The internal red-team result mainly shows how many created anomalies were found. Detecting 132 of 140 abnormal paths does not tell us how often normal paths were wrongly flagged. The paper also reports 1,087 tool responses, but responses and complete execution paths are different counting units. More path-level counts are needed to judge false alarms in this test. This concern does not apply to the main benchmark, which does include normal test paths.
4.The component tests are narrower than the main comparison. Table 3 removes the structural and semantic components only for clinical triage with two detector models. These results support both components in that setting, but do not show whether the same pattern holds for procurement. The paper also does not give processing time or show how the results change when fewer normal logs are used to learn the rules. These details would help assess its practical use.
Questions for authors
-
What information does the direct LLM baseline receive? Does it get normal examples or a summary of normal behavior from the same historical logs? If feasible, could you compare TRACEAEGIS with a suitable existing trace-based detector from Section 5?
-
Do the profiling and test sets share request templates, even though their logs are separate? Could you also test a simple detector that uses only the number of tool calls, given the length differences in Table 1?
-
In the internal red-team test, were normal traces also checked? If so, how many were checked and how many were wrongly flagged? Which LLM produced the reported 132/140 result?
-
Table 3 tests the two components only on clinical triage. Could you repeat the same comparison on procurement with one of the same LLMs, removing each component in turn?
-
How long does it take to learn the rules from the normal logs, and how long does it take to check one new trace? If you repeated the LLM-based steps, how much did the detection results change?
2 comments
Dear Reviewer F8Vq, thank you again for your helpful feedback, and we sincerely apologize for our late response. We would be grateful to learn whether our rebuttal resolves your concerns, and any further suggestions for improving the paper would be most welcome. Thank you for your time and consideration.
Response to Reviewer F8Vq
The direct LLM baseline receives the candidate tool-call records, including inputs and outputs, together with a scenario-specific prompt describing the expected workflow and what constitutes anomalous behavior.
To address the difference in access to historical information, we added a RAG baseline that retrieves the top three complete normal traces from the same profiling corpus and provides them to the detector LLM. We also added comparisons with Inductive Miner and an adapted AgentArmor implementation. As reported in our response to common questions, TraceAegis achieves higher clinical F1 than these baselines with both backbones.
Our profiling/test split is trace-level and may share request templates. As detailed in our response to Reviewer Cg4o on Data Generation and Generalization, normalized full-trace hashes do not overlap, and 41.33% of benign clinical test traces follow previously unseen complete tool-call paths. This establishes path variation, although it does not establish template-disjoint evaluation.
We also evaluated a length-only detector using the number of tool calls as its sole feature. For each scenario, we reserved 200 normal profiling traces for calibration and used the 2.5th and 97.5th length percentiles as bounds.
These results indicate that trace length can identify some anomalies, but its limited recall shows that length alone is insufficient for detecting the structural and semantic anomalies in the benchmark.
The industry red-team results were obtained using DeepSeek-V3. The response-level FPR is 1.9% in the set of 1,087 tool responses. At the execution-path level, the evaluation includes only anomalous traces, of which TraceAegis detects 132/140 (94.3%). We therefore report recall at this level.
We repeated the component ablation on procurement using GPT-OSS-120B. The results are shown below.
Removing BC reduces F1 from 93.60% to 85.63%. Removing HS causes a larger decline to 62.85%, with both precision and recall decreasing. These results are consistent with the clinical ablation and support the contribution of both components in procurement.
We measured the LLM request time for rule learning and detection separately on clinical triage using DeepSeek-V4.1-Flash-1017. Learning from 1,000 normal traces required an amortized 10.29 seconds per profiling trace, including batched extraction and shared rule summarization. Once the profile was built, detection required 23.79 seconds per test trace on average across the 600 test traces.
As reported in our response to Reviewer Cg4o on sensitivity, we repeated profiling and evaluation across different profiling sizes. The F1 standard deviations remained below 1.7 percentage points for both models, indicating consistent performance across repetitions.