- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies misuse monitoring for LLM agents, bringing decomposition attacks and prompt injection attacks into a unified framework for evaluating agent trajectories. A monitor receives interval credit only if its first alert falls within this window. The main finding is that monitors focused on the agent's actions distinguish successful injection from refusal more effectively than monitors focused on input content.
Critical strengths
-
Distinguishing eventual detection from timely intervention better reflects agent safety requirements than classifying entire trajectories alone. This is an important and practically relevant problem.
-
The paper evaluates multiple monitoring configurations and models, with additional analyses of calibration, cost, and window sensitivity.
-
The appendices acknowledge annotation disagreements, generation artifacts, and the influence of evaluation cadence.
Critical weaknesses
-
The core metric lacks sufficient justification. Reasonable alerts during clearly malicious preparation can receive zero credit. Low interval credit may therefore reflect useful early intervention rather than poor monitoring. Conversely, an alert inside the window may arrive after some harm has already occurred.
-
The claimed methodological advantage is confounded. Action framing changes both the judgment target and evaluation cadence. Matching cadence raises Gemma's sequential monitor interval credit from 0.166 to 0.410, close to the action variant抯 0.433, weakening attribution of the improvement primarily to framing.
-
Synthetic traces may make detection unrealistically straightforward. Successful injection continuations are instructed to explicitly announce the malicious action and immediately execute it. Delayed, concealed, and interleaved attacks are insufficiently represented.
Questions for authors
Could you rebuild the refusal twins using the final evidence-onset labels and report whether the conclusions remain unchanged? How sensitive are the timing results to annotation disagreements?
2 comments
Response to Reviewer ZyLs (2/2): diversified attacks, rebuilt refusal twins and label sensitivity
More diversified attacks
The submitted version covers part of this. Attacks interleaved with benign steps have their own split (decomposition_hard, §4.1; App. D.6). We had also run an adversarial study that rewrites the finished traces to hide the attacks better (while keeping the harm). This succeeded in at most 5 of 40 cases (App. E.5, Table 17). We now further add two tests:
- No announcement. When we delete all the assistant text and keep only the tool calls, then
sequential_actionachieves 0.969 AUC on synthetic traces and 0.935 on real AgentDojo runs. - Concealed, delayed attacks. We generated traces where the agent never mentions the injection prompt, takes at least two user task steps first, and also keeps its final reply about the user's task. The
sequential_actionarm's AUC is 0.989 and it flags every attack.
The baseline arm (which sees one message at a time) drops in AUC from 0.938 to 0.846, so it does partly rely on the announcement. The concealment behaviour is also still prompted, so this does not represent an adaptive adversary.
Refusal twins and labels
Our submitted version flagged this issue (App. C.2, "Refusal twins"): the twins were created as per an older version of the onset labels. We have now rebuilt all refusal twins on the final labels, and results have been updated in §6 and App. E. All our conclusions still hold:
sequential_actionnow flags 47–72% of E-twins (refuse immediately at E) on 8 of 9 models (previously 28–57%).- The action-framed arms have an AUC of 0.67–0.86 on separating harmful traces from their twins (previously 0.76–0.91).
- The change comes almost entirely from traces where the onset was updated to be placed later.
We reported rater reliability (App. C.4.1) and a grace-period sweep showing how credit moves if E sits a few messages late in the submission (App. D.10, Figure 9) to address label sensitivity. Now in App. H.6, we find that alternative labellings move pooled interval credit by at most 0.055 per arm (earlier labels), 0.003 (cross-family labels), 0.037 (shifting a random third of labels by one step), and 0.006 (author-labelled subset). Action-framed arms perform better than content-framed ones. The best arm is still the same in every case. Only large systematic shifts of the labels affect the scores substantially.
All revisions are listed in our general response, and revised text is highlighted in blue.
Response to Reviewer ZyLs (1/2): justifying interval credit and matched cadence
We thank the reviewer for a careful review. We have added some new experiments to Appendix H based on your concerns.
Justifying interval credit
We agree that interval credit is strict. We reported recall next to interval credit throughout the submission, along with the split into early, timely and late flags (§3.4, Figure 4; App. E.1, Figure 10). We also inspected some of the early flags. 18 of 21 fell on preparation, such as drafting a phishing message, so we treat the interval credit as a lower bound on detection (App. E.1). We have now also re-scored every arm with nine different ways to assign monitor credit (App. H.3):
§3 now presents interval credit as the strictest of this family of rules, and App. H.3 shows recall as the most lenient.
Experiments that match the cadence
As the reviewer notes among the strengths, the submitted appendix already reports a control for cadence (App. D.10, Table 12). We agree with the claim for decomposition, and the paper reaches the same conclusion (App. E.1, §6). There, both framings catch almost the same traces, and the timing advantage of
sequential_actioncomes mostly from scoring only at the agent’s messages.We have now added this control for injection, where our framing claim matters more (App. H.5). When we match the cadence of arms on injection, the AUC for the (Gemma)
sequentialarm rises from 0.521 to 0.646, but is still far belowsequential_action(0.985). But when we then add one sentence telling the content-framed monitor to judge the assistant's actions (thus changing the judgement target), it recovers most of the remaining gap (86% on Gemma, 91% on Qwen3.6).So the two changes (changing the cadence vs changing the framing) have separate effects. Cadence mainly changes timing on decomposition. The framing (or judgement target) mainly changes detection on injection. So action-framing allows one monitor to perform well on both settings. §5 now states this more clearly.