- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes JANUS, a training framework that combines simulated long-horizon trajectories with Coupled Anticipation and Adjudication Reinforcement Learning (CoAA-RL), jointly training future prediction and safety judgement. The paper studies predictive guarding for long-horizon agent safety, where risks arise from delayed consequences rather than immediately apparent harmful intent. The resulting model, VANGUARD, anticipates safety-relevant continuations and uses them to identify unsafe behaviour before execution. Experiments across four benchmarks show improved protection against unsafe agent behaviour, while benign task completion is preserved on AgentDojo.
Critical strengths
-
The training data covers risks originating from users, external environments, and the agent’s own mistakes, giving the approach broader scope than defenses focused only on malicious prompts.
-
VANGUARD achieves the lowest attack success rate on all four benchmarks, showing consistent improvements across the evaluated safety settings. The improvement is particularly substantial on LPS-Bench, where ASR decreases from 32.3% for the strongest competing defence to 7.5%. On AgentDojo, VANGUARD reduces ASR from 16.6% without a guard to 5.4%, while maintaining the same benign-task success rate of 68.0%.
-
The ablations provide useful evidence for both anticipation and reward coupling. Removing anticipation during training or withholding predicted summaries at inference worsens safety and benign-task performance, while similarity-only, utility-only, and decoupled training also underperform the full method.
Critical weaknesses
-
Benign-task utility is reported only for AgentDojo. Consequently, the table does not establish whether the safety improvements on the other three benchmarks come at the cost of blocking legitimate tasks.
-
Results are presented without confidence intervals or variability across repeated runs, making it difficult to assess the reliability of smaller improvements, such as the reduction from 6.2% to 5.4% ASR on AgentDojo.
-
The paper does not report computational overhead, so the performance gains cannot be assessed alongside the additional cost of prediction and adjudication.
-
ASR measures whether harm occurred but does not reveal how many steps before harm the guard intervened. The prefix experiments provide partial evidence, yet do not report detection lead time relative to the first harmful action. Lower ASR alone does not establish better foresight. Prefix length does not directly measure intervention timing. The table (3) does not show how far before the first harmful action the guard intervenes. Reporting detection lead time would more directly substantiate the claim of anticipating delayed harm.
-
Early prediction is less effective on planning tasks. In table3 at 25% prefix on LPS-Bench, VANGUARD’s ASR is 49.8%, compared with QwenGuard’s 33.2%. Its advantage therefore does not extend to the earliest observation budget across all settings.
-
The related work explicitly discusses SafePred, which predicts future risks through world modeling, but the experiments do not compare against it. This leaves the empirical distinction from existing predictive guarding insufficiently established.
-
The benefit of forecasting is not isolated from additional inference computation. The method performs separate anticipation and adjudication generations but does not compare against a direct safety judge given a comparable inference budget. Such a comparison would help establish whether explicit forecasting accounts for the improvement.
-
Generalisation across execution agents remains unclear.
Overall, the paper presents a promising forecast-then-judge guard, with strong reported safety results and useful component ablations. Its most convincing contribution is coupling forecast training to downstream safety classification.
Questions for authors
see the weaknesses section
5 comments
Response to Reviewer CMck (Part 2/2)
W4: Direct detection lead time.
Following your suggestion, we directly measure warning time before the first harmful action. The evaluation replays prefixes of unguarded reference trajectories and measures lead as , where h is the first annotated harmful action and t is the blocking decision. Blocking immediately before execution has lead 0.
At a validation-calibrated FBR target of 5.0%, delayed-planning EDR@1/2/3 is 65.0%/46.0%/29.0% for VANGUARD versus 36.0%/18.0%/8.0% for TS-Guard. Mean lead is 2.1 versus 1.0 actions, with coverage of 89.0% versus 68.0%. EDR includes missed detections among all 200 delayed-planning cases. Mean lead is conditional on detection, so coverage is needed to interpret it.
VANGUARD improves both detection coverage and warning time on the replay set. The gains at all three lead thresholds provide direct evidence for earlier intervention and complement the closed-loop ASR results. We will include the calibration settings, actual test FBR, and annotated action indices with this evaluation.
W5: The 25% LPS result.
We agree with this point. At 25% prefix, VANGUARD's 49.8% ASR is worse than QwenGuard's 33.2%. Its advantage in Table 3 begins at 50%, reaching 27.9%, 15.1%, and 7.5% at 50%, 75%, and 100%. We will revise the Table 3 discussion to state this dependence on the observation budget.
W6 and W7: SafePred and additional inference computation.
We added both SafePred and a two-call direct judge under matched evaluation conditions. The methods use the same execution agent and tasks, with matched visible history, decision points, and total output cap:
| Method | LPS ASR | AgentDojo utility |
|---|---|---|
| SafePred, matched block-only | 12.6% | 66.0% |
| Two-call direct judge | 14.0% | 66.0% |
| VANGUARD | 8.1% | 67.0% |
-
Matched baselines. VANGUARD achieves the lowest LPS ASR and highest AgentDojo utility in this comparison. SafePred uses a block-only adaptation with native plan updates disabled, giving both methods the same intervention interface. The two-call direct judge spends its budget on two safety judgments. We will provide the judge checkpoint, inputs to each call, and aggregation rule alongside the SafePred guard configuration.
-
Summary content. Holding VANGUARD's adjudicator fixed, within-class summary shuffling raises LPS ASR from 7.5% to 15.6%. The original no-summary ablation also increases LPS ASR to 16.3% (Table 2, lines 331 to 334). These tests show the value of supplying the adjudicator with the corresponding future content. The two-call comparison above fixes the call count and output cap, with actual inference costs reported in W3.
The controlled comparisons link the safety gain to useful future content. VANGUARD achieves lower ASR than the two-call judge under the same output cap, with the additional token use and latency quantified above. Disrupting its summary content also reduces safety. The content ablations use the original 7.5% configuration, while the matched evaluation uses the 8.1% configuration. We will list these configurations alongside the results.
The LPS evaluation uses 570 instances and the episode-based ASR definition in Eq. 13 (lines 674 to 679 and 686 to 690). We will add the repository revision, evaluator version, and outcome counts, including the treatment of technical failures and guard-terminated trajectories, to the evaluation details.
W8: Transfer across execution agents.
We keep the guard weights, prompts, and intervention rules fixed and replace the execution agent:
| Execution agent | LPS ASR: no guard / TS-Guard / VANGUARD | AgentDojo utility: no guard → VANGUARD |
|---|---|---|
| Qwen3-235B-A22B-Instruct-2507 | 76.1% / 27.2% / 6.5% | 75.3% → 74.2% |
| Llama-3.3-70B-Instruct | 81.4% / 30.2% / 8.9% | 70.1% → 69.1% |
The same guard reduces LPS ASR substantially with both additional execution agents and outperforms TS-Guard on each. AgentDojo utility remains close to no guard, decreasing by 1.1 and 1.0 points. Together, these results support reusing VANGUARD across the evaluated execution-agent sizes and families with fixed weights, prompts, and intervention rules.
Reference: SafePred.
Follow-up to Reviewer CMck
Dear Reviewer CMck,
Thank you again for your detailed review. Following your suggestions, we added benign utility evaluations, repeated runs with a paired confidence interval, and measured inference costs. We also reported direct detection lead time, comparisons with SafePred and a two-call judge, and results with two additional execution agents.
We would appreciate your thoughts on whether our response addresses your concerns. Please let us know if any point needs further clarification.
Best regards, Authors of Submission 50365
Response to Reviewer CMck (Part 1/2)
Thank you for recognizing the broad risk coverage, safety improvements, and evidence for reward coupling. Following your suggestions, we added utility evaluations, repeated runs, timing and cost measurements, and matched comparisons with predictive and direct-judgment baselines.
VANGUARD preserves AgentDojo utility at 68.0%, equal to no guard, while reducing ASR from 16.6% to 5.4%. We also evaluate 100 confirmed-safe counterparts per additional setting:
The counterparts preserve the legitimate task objective and success criterion. Utility measures successful completion, following lines 681 to 685, while FBR measures the fraction of safe tasks terminated by the guard. Safe-task status is assessed separately because a benign user request can still lead to unsafe execution, particularly on LPS.
VANGUARD reduces false blocking across all three settings and keeps utility within 2, 2, and 3 points of no guard. Utility improves over TS-Guard by 5 points on Agent-SafetyBench and 3 points on LPS. On AgentLAB, utility is 67.0% versus 68.0%, with lower FBR at 5.0% versus 7.0%. The additional evaluations therefore support a favorable safety and utility balance across these settings.
We added repeated evaluations and a paired task-bootstrap interval. Across 3 runs with fixed guards and independent execution seeds, AgentDojo ASR is 5.6 ± 0.4% for VANGUARD and 6.4 ± 0.5% for LlamaFirewall. The 95% interval for VANGUARD minus LlamaFirewall is [−2.1, 0.5] percentage points.
The AgentDojo difference is small and its interval includes zero. On LPS, repeated ASR is 7.8 ± 0.7% for VANGUARD versus 53.2 ± 1.1% for LlamaFirewall. The larger observed gap on LPS complements the utility and timing evidence for long-horizon safety.
The repeated runs reuse fixed guard checkpoints and vary execution seeds. They add an assessment of execution variability to the original single-run setup (lines 700 to 701). We will report the repeated results and interval alongside the main table.
Inference uses two sequential generations from the same 8B policy. The guard first predicts a future summary and then judges safety conditioned on that summary (lines 304 to 314). The 8×8 rollout sampling is used during training (lines 704 to 707).
Latency is measured on one H200 GPU in BF16 with batch size 1, a 4,096-token prefix, and a total output limit of 1,536 tokens per decision. The measurements include both stages and repeated context processing:
VANGUARD uses 168.7 output tokens per decision, with a median latency of 2.29 s. Compared with the two-call direct judge, it uses 55.5 more output tokens and adds 0.50 s to median latency. The corresponding LPS ASR falls from 14.0% to 8.1% in the controlled comparison below. End-to-end task time increases by 12.8% over no guard in the measured workload. These measurements quantify the safety benefit alongside the additional cost of anticipation.