Pith.

Cryptography and Security · arXiv:2610.06401 v2 · submitted 5 Oct 2026

RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents

Mohamed Dhouib, Clement Elliker, Alexi Canesse, Maël Jenny, Lucas-Andrei Thil, Mahammed El Sharkawy, Sonia Vanier, Elie Bursztein

The paper says

“Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack success rates, but often at the cost of general capabilities.”

more of the abstract

We show that training-based defenses induce substantial drift in the model's output distribution, altering its behavior even in benign settings and providing a potential mechanism for utility degradation. We further identify a failure mode of these defenses: On benign tool-use tasks, the model refrains from a step needed to finish an authorized task, particularly when that step is indicated by a tool output. To address these limitations, we introduce RAISED (Robust Attack Invariance through Self-Distillation), a training framework that combines self-generation and self-distillation. The model first generates its own tool-use scenarios, with an emphasis on cases where task completion requires acting on legitimate guidance from tool outputs. Then, through self-distillation, the student is trained to match the teacher's clean-context behavior on both clean and injected variants of the same trajectory. RAISED substantially reduces the attack success rate of prompt injections in tool responses while, unlike prior training-based defenses, preserving utility on both agentic and general-purpose benchmarks.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 6 Oct 2026 · of version 1 of the paper; version 2 is newer · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

Holds up, with conditions. A solid, honestly-scoped training-time defense with a clean controlled ablation; the open question is how far the invariance learned on self-authored injections generalizes beyond the three benchmark corpora used for scoring. This line is wrong

1 major objection · 4 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the references say.

The paper says, at Section 3.2 / Eq. (1); Section 5.1 / C.5.1; Section F; Section 7.1, Table 1

The review did not quote this passage.

Pith says: Objection 1 of 1 · major

The abstract and Section 7.1 claim that RAISED 'substantially reduces the attack success rate of prompt injections in tool responses,' and the method is framed around the channel-level invariance of Eq. (1), i.e., insensitivity to any inserted adversarial span. The supporting evidence is restricted to three fixed corpora (InjecAgent, AgentDojo, AgentDyn), while all training-time injections are written by the defended model itself, post-hoc, in its own linguistic register, with knowledge of the exact tool outputs and attacker tooling (Section C.5.1).

more of objection 1

The paper candidly delimits the adaptive frontier in Section F [b669-b680], but no passage addresses the middle ground within the static threat model: fresh static injections authored by independent writers, in other styles, deeper embedding positions, or multi-part forms. Because Eq. (3) penalizes deviation from the clean distribution equally whether the student learns true span-insensitivity or a corpus-level shortcut (e.g., recognizing its own prose style or scenario-local goals), the ~1% ASR values in Table 1 do not by themselves establish the general invariance the abstract and Eq. (1) claim; the diversity across the three benchmark corpora mitigates but does not close this gap. I ask the authors either to (a) re-attack the released RAISED checkpoints with a held-out set of fresh, independently authored static injections (e.g., different styles, deeper embedding, multi-part instructions) and report ASR/U/U_atk in the Table 1 format, or (b) explicitly scope the abstract and Section 1 claims to the evaluated attack distributions and state the static-distribution-shift transfer as an open question, in the same manner Section F handles adaptive attacks.

4 minor objections

The paper says, at Section 4.1 / B.1

Pith says: minor objection 1 of 4

The distribution-drift analysis measures next-token KL on 500 standalone non-tool QA questions, whereas the paper's utility argument (Contribution 1) concerns agentic tool-use behavior. The paper correctly hedges drift as only a 'potential mechanism' for utility loss, but a sentence noting that drift on tool-use contexts was not measured, and pointing to the Section B.2 examples as the qualitative evidence on that channel, would tighten the link between the two parts of Contribution 1.

The paper says, at Section 5.2

Pith says: minor objection 2 of 4

The training input h'_i is drawn from {h_i, ~h_i}, but the 0.5 injection ratio is stated only in Section C.5.1; a one-line note in Section 5.2 would let readers of the main text see the clean/injected balance without consulting the appendix.

show 2 more

The paper says, at Abstract / Section 1

Pith says: minor objection 3 of 4

The abstract's 'unlike prior training-based defenses' is supported for the SFT and SecAlign++ baselines actually evaluated, but other training-time defenses (e.g., Jatmo, instruction-hierarchy training) are not compared; consider hedging to 'the training-based defenses we evaluate' to match the evidence.

The paper says, at Section 7.1

Pith says: minor objection 4 of 4

The main-comparison SecAlign++ checkpoint uses 313 steps over 5,008 examples while RAISED trains on 10,000 trajectories. The paper addresses this asymmetry in Sections C.4, D.8, and the Section E ablation, but a single pointer sentence near the Table 1 discussion would prevent readers from misreading the main comparison as precisely budget-matched.

What would settle it

Take the released RAISED checkpoints (Gemma, Nemotron, Qwen) and the public AgentDojo/AgentDyn episode harness, unchanged. Before any interaction with the defended checkpoints, have a different strong model, given only the episode's tool outputs as the attacker channel, write fresh static injections with varied styles, mid-document embedding, and multi-part instructions, inserted at the original positions. Run the frozen checkpoints once, with no retraining, and compare ASR and U_atk to Table 1 and D.6. If ASR stays near 1% with U_atk near U, channel-level invariance is confirmed and the concern fails; if ASR rises above roughly 10%, the headline overstates robustness to unseen static attacks and the transfer claim as stated should be narrowed.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 6 Oct 2026

  1. Reader holds up, with conditions confidence moderate
  2. Skeptic agrees 4 min 24 s · 34,681 tokens read, 19,438 written
  3. Editor wrote the verdict above 40 s · 35,636 tokens read, 3,057 written
  4. Referee major revision: 1 major objection, 4 minor 1 min 15 s · 34,909 tokens read, 9,907 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

RAISED is a solid training-time defense paper. The central claim — that clean-context self-distillation cuts indirect prompt-injection ASR to roughly one percent on three independent benchmarks while preserving benign agentic and general utility — holds up on the evidence shown. It deserves a serious referee.

What is actually new: the controlled distribution-drift analysis (Section 4.1 / B.1), the named behavioral failure mode where defended models stop acting on legitimate tool-output guidance (4.2 / B.2), and the application of consistency training to multi-turn tool-use trajectories with self-generated scenarios and attacks. The strongest evidence is Section E, which holds the data and input representation fixed and varies only the objective: self-distillation preserves more agentic utility than SFT or SecAlign++'s DPO at similar ASR, and the self-generated trajectories add a further utility gain. That is the right way to separate the idea from the data pipeline.

The robustness numbers are externally grounded. ASR is measured on InjecAgent, AgentDojo, and AgentDyn, whose attacks are human-authored static injections the defended model never saw, so the circularity burden is genuinely low. The paper is also unusually candid about scope: adaptive attacks are explicitly out of scope, the failure-mode examples are labeled illustrative, and the teacher-quality bound is stated.

Soft spots, in proportion. First, a real generalization gap: training attacks are written by the defended model itself, so the learned invariance is demonstrated on three corpus-specific attack distributions, not shown to be channel-level. The paper scopes honestly to static attacks, but nothing addresses fresh static injections written by a different author in a different style. The abstract's "substantially reduces the attack success rate of prompt injections in tool responses" slightly over-covers that gap. I read this as a generalization caveat rather than a broken central claim, but a third-party re-attack of the released checkpoints with independently rewritten injections would settle it, and I would ask for that.

Second, the SecAlign++ comparison uses the 313-step checkpoint against a longer RAISED budget. This is disclosed and quantified in D.8, and the utility-damage story justifies the choice, but the headline table still reads as asymmetric. A matched-budget row in the main table would fix it. Third, smaller items: the failure mode has no prevalence estimate, which the authors admit; the per-block internal-state analysis (D.7) is suggestive but light; and the code link has no commit hash, so pin it.

Who this is for: anyone working on agent security or training-based defenses. The drift measurement and the controlled ablation are worth citing even independently of the method. My recommendation: accept for peer review. The central claim is supported, the limitations are disclosed, and the remaining asks are concrete rather than structural.

The strongest objection

For the central claim to be more than a report about three fixed corpora, the student must acquire channel-level invariance: for any adversarial span inserted into a tool observation, next-token behavior equals clean-context behavior. Training-time span diversity comes exclusively from self-authored attacks: the defended model writes them post-hoc, with knowledge of the exact tool outputs and attacker tooling, in its own linguistic register (Section C.5.1). Eq. (3) punishes deviation from the clean distribution on injected contexts equally whether the student learns true span-insensitivity or a corpus-level shortcut, e.g., recognizing its own prose style, edge placement, or scenario-local goals. The three evaluation corpora (InjecAgent, AgentDojo, AgentDyn) are genuine and independent mitigations: their attacks are human-authored, static, and placed in realistic content, and ASR falls to roughly 1%. The untested middle ground lies between these corpora and the adaptive attacks excluded in Section F [b669-b680]: fresh static injections written by a different author with the same environment access, using other styles, deeper embedding, or multi-part instructions. The paper candidly delimits the adaptive frontier, acknowledges the teacher-quality bound (Section G) and the illustrative scope of the failure-mode examples (B.2), but no passage addresses this static distribution-shift gap, so the abstract's broad phrasing, 'substantially reduces the attack success rate of prompt injections in tool responses,' exceeds what the current evidence directly covers.

Good-faith reading: the central engineering claim is that training a student to match the frozen base model's clean-context next-token distribution on both clean and injected versions of its own trajectories (Eq. 3) realizes the invariance target of Eq. (1), B-theta(c-tilde) congruent B-theta0(c), thereby reducing a static attacker's success while preserving benign utility. That claim is corroborated where it is directly testable: three independently authored benchmark corpora, three model families, three seeds, and a controlled ablation (Section E) holding data and inputs fixed, in which self-distillation dominates SFT and DPO on utility at comparable ASR. The KL-drift figures (0.0010 vs 0.044/0.029, Fig. 2; longer-schedule values in B.1) are consistent with the mechanism, and the internal-state analysis (D.7) shows reduced injection sensitivity. Acknowledged limitations, teacher-bounded quality (G), illustrative rather than prevalence-estimating failure mode (B.2), and static-only threat model (F), are stated candidly and are not treated as defects. The remaining soft spot is the one the reader flagged, sharpened here: within the static threat model, the training distribution of adversarial spans is generated entirely by the defended model itself (C.5.1), and the evaluation corpora, while independent, are exactly the fixed corpora against which the claim is made. What is never varied is the attack-writing process itself: style register, embedding depth, multi-part structure. Eq. (3) would reward a corpus-level shortcut as much as genuine span-insensitivity, and the controlled measurements cannot distinguish these. This is not an internal inconsistency; it is a precisely delimited generalization gap at the boundary of the paper's claims, which the paper's candor covers on the adaptive side but not on the fresh-static-attack side. The paper also discloses the SecAlign++ budget asymmetry and quantifies the 625-step trade-off on Nemotron (D.8), though only qualitatively for Gemma; that is a secondary, disclosed fairness issue rather than the primary threat to the central claim. If the proposed re-attack test shows ASR remains near 1% with U_atk near U across the three models, the central claim is robust within its scope and the paper warrants acceptance-type handling with the reader's requested code release and matched-budget tables. If ASR rises materially, the headline should be narrowed to the tested corpora and the verdict should move toward restricted-scope handling. Without running the test, the reader's CONDITIONAL disposition is the right verdict, so no change is made.

The referee's report

If the results hold, the paper makes two useful contributions to the prompt-injection defense literature. First, it provides concrete evidence, including a clean controlled ablation (Section E) that holds the trajectories, inputs, and budget fixed while varying only the objective, that clean-context distribution matching preserves more agentic utility than SFT or the DPO objective used by SecAlign++ at similar attack success rates; this is the kind of controlled comparison the area needs and it is done properly with three seeds. Second, the evaluation is grounded externally: ASR and utility are measured on three established benchmarks (InjecAgent, AgentDojo, AgentDyn) whose attacks are human-authored and independent of the defended model, so there is no circularity in the robustness claim. The paper is also commendably honest about scope: it explicitly excludes adaptive attacks (Section F), acknowledges the teacher-quality bound (Section G), and labels the behavioral-drift examples as illustrative rather than prevalence estimates (Section B.2). The reproducibility statement and released code support verification.

Pith's reading of the paper (a machine's summary, not the authors')

Tool-using language-model agents must act on content they pull from emails, webpages, and APIs, and attackers can hide instructions inside that content to redirect the agent. Prior attempts to train away this vulnerability made models more resistant but also changed their ordinary behavior, often leaving authorized tasks unfinished. This paper tries to establish that the right training target is the model's own clean behavior: in RAISED, a frozen copy of the model writes its own tool-use tasks and its own attack strings, and a trainable copy is trained to make the same next-token decisions the frozen copy would make on the clean task even when an injection has been dropped into a tool response. On the AgentDojo benchmark with Gemma, the paper reports attack success falling from 39.5% to 1.0% and utility under attack rising from 64.0% to 80.5%, with benign utility down just one point — matching a leading preference-tuning defense without its seven-point utility loss — and it reports the same pattern across three model families. If the learned invariance transfers to attacks and content the model never wrote itself, agents can be hardened against injected instructions without paying the usual capability tax.

What carries the argument. The load-bearing mechanism is two-stage. Stage one, self-generation, has the frozen base model create the training distribution: an executable scenario with 3–6 tools, a user request needing a chain of dependent calls, and a success check, with generation steered toward "surfaced guidance," "recovery/completion," and "follow-through" structures so that many benign tasks require acting on legitimate tool-output instructions; the model then solves and verifies each scenario and, in a separate attacker role, writes an injection and chooses where in its own tool output to insert it. Stage two, injection-augmented self-distillation, trains the student by minimizing $\mathbb{E}_{\tau \sim \mathcal{D}} \sum_{i \in I(\tau)} D_{\mathrm{KL}}(q_i \| p_\theta(\cdot|h'_i))$ with $h'_i$ either the clean history $h_i$ or the injected history $\tilde{h}_i$, where $q_i$ is the teacher's clean-context next-token distribution. On clean contexts the objective anchors the student to the base model; on injected contexts the same target makes the student insensitive to the adversarial span. Because the legitimate tool content is unchanged, the model learns to distrust the injected portion rather than the tool-output channel as a whole.

Core claim. The central claim is that prompt-injection resistance and benign utility are not locked in a trade-off when the defense is framed as invariance rather than retraining. The paper's target is the identity $B_ heta( ilde{c}) \equiv B_{\theta_0}(c)$: the defended model's behavior on an injected context should equal the base model's behavior on the corresponding clean context, so attack success falls to the level the base model reaches by accident while utility under attack matches clean utility. The discovery is that this can be realized by having the model itself supply the training signal. A frozen copy of the base model acts as generator, solver, and attacker: it writes an executable tool-use scenario steered toward cases where finishing the authorized task requires acting on legitimate guidance returned by a tool, solves the scenario through its normal tool-calling interface, verifies success against a generated check, then writes its own injection string and plants it in one of its own tool outputs. A trainable student is then trained with a KL objective — a standard measure of how far two probability distributions are apart — to match the frozen model's clean-context next-token distribution (the top 256 token probabilities plus one residual bucket) on both clean and injected versions of the same trajectory. The paper reports per-token forward and reverse KL from the base model of about 0.0010, versus 0.044 for SFT and 0.029 for DPO, and reports that on AgentDojo with Gemma attack success falls from 39.5% to 1.0% while benign utility drops from 84.5% to 83.5%.

The premise it rests on. The claim stands or falls on transfer: resistance learned from scenarios and attacks that the base model writes for itself must generalize to attacks written independently by real adversaries, and preserved willingness to act on self-generated tool-guidance cases must predict preserved utility on real workloads — if the model-written attacks are easier than genuine ones, or the self-written tasks are closer to the benchmarks than to deployment traffic, the headline attack-success and utility numbers overstate real-world robustness.

If the paper is right (Pith's inferences, not the authors')

Attack success rate alone can mislead: the filtering baseline PromptGuard2 cuts AgentDojo ASR from 39.5% to 16.1% yet drops utility under attack from 64.0% to 42.9%, so ASR, benign utility, and utility under attack should be reported and read together.

Per-token KL divergence from the base model is a cheap early-warning proxy for capability drift: SFT and DPO sit at 0.044 and 0.029 while self-distillation sits at 0.0010, and the two preference- and SFT-based methods drift further with more training while self-distillation does not.

Defensive training targets should come from the model's own distribution whenever the desired behavior already exists: externally authored SFT targets and DPO preference pairs carry a likelihood-displacement risk that preserving clean-context behavior avoids.

Because RAISED preserves rather than improves the base model, the defended model inherits the base model's errors, so the method is a defense against context influence rather than a general alignment or safety fix.

The method also helps in low-ASR regimes: on Qwen, where the undefended model already achieves 5.8% ASR on AgentDojo, RAISED still pushes it to 0.9% while keeping general and agentic scores close to the Vanilla checkpoint.

Beyond the paper: because the training attacks are written by the model being defended, the reported roughly 1% ASR may understate performance against injection styles the base model would never write; a natural stress test is to evaluate RAISED on an injection suite authored by a different model or by humans without further fine-tuning.

Beyond the paper: the same clean-context self-distillation could be applied to other untrusted-channel threats — phishing instructions in email text, web content in browsing agents, or poisoned tool descriptions — wherever a trustworthy clean behavior already exists to be preserved by matching the base distribution.

Beyond the paper: the measured KL-to-utility relationship suggests a testable rule of thumb — defenses keeping per-token KL from the base model below roughly 0.002 should show little benign utility loss, while drift above roughly 0.03 should show measurable degradation — which could be checked across other models and benchmarks.

Beyond the paper: the authors restrict their empirical claims to static attacks, so an adaptive attacker with query access and an optimizer over injection strings sits outside the reported numbers; the roughly 1% figure should not be quoted for adversarial red-teaming settings.

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack success rates, but often at the cost of general capabilities. We show that training-based defenses induce substantial drift in the model's output distribution, altering its behavior even in benign settings and providing a potential mechanism for utility degradation. We further identify a failure mode of these defenses: On benign tool-use tasks, the model refrains from a step needed to finish an authorized task, particularly when that step is indicated by a tool output. To address these limitations, we introduce RAISED (Robust Attack Invariance through Self-Distillation), a training framework that combines self-generation and self-distillation. The model first generates its own tool-use scenarios, with an emphasis on cases where task completion requires acting on legitimate guidance from tool outputs. Then, through self-distillation, the student is trained to match the teacher's clean-context behavior on both clean and injected variants of the same trajectory. RAISED substantially reduces the attack success rate of prompt injections in tool responses while, unlike prior training-based defenses, preserving utility on both agentic and general-purpose benchmarks.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-10-06

The authors' main claim, as the classifier picked it out 1.00

“RAISED substantially reduces the attack success rate of prompt injections in tool responses while, unlike prior training-based defenses, preserving utility on both agentic and general-purpose benchmarks.”

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.07 · states limitation 0.12 · human participants 0.03 · controlled comparison 0.53 · randomized assignment 0.02 · states quantitative result 0.06 · compares with prior results 0.96 · mentions code or data availability 0.03

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. background 1.00 0.06 0.02 asserted 1.00
Existing training-time defenses can reduce attack success rates, but often at the cost of general capabilities. background 0.89 0.04 0.02 asserted 0.84
We show that training-based defenses induce substantial drift in the model's output distribution, altering its behavior even in benign settings and providing a potential mechanism for utility degradation. result 0.84 0.87 0.06 asserted 0.94
We further identify a failure mode of these defenses: On benign tool-use tasks, the model refrains from a step needed to finish an authorized task, particularly when that step is indicated by a tool output. result 0.90 0.86 0.04 asserted 0.99
To address these limitations, we introduce RAISED (Robust Attack Invariance through Self-Distillation), a training framework that combines self-generation and self-distillation. contribution 0.89 0.85 0.08 asserted 0.99
The model first generates its own tool-use scenarios, with an emphasis on cases where task completion requires acting on legitimate guidance from tool outputs. method 1.00 0.79 0.03 asserted 0.97
Then, through self-distillation, the student is trained to match the teacher's clean-context behavior on both clean and injected variants of the same trajectory. method 1.00 0.84 0.05 asserted 0.98
RAISED substantially reduces the attack success rate of prompt injections in tool responses while, unlike prior training-based defenses, preserving utility on both agentic and general-purpose benchmarks. result 0.99 0.95 0.94 asserted 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.98

What was examined, and what was not

Sources read

  • arXiv listing abstract v1

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-10-06: 1 request, 6,260 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (7)
Figure 1 of the paper
Figure 1. Overview of RAISED. The base model generates its own tool-use tasks and injections (Stage 1). The student is then trained to match the base model’s clean-context distributions on injected contexts (Stage 2), making it invariant to the injection. 2024). Prevention can also be enforced at the system level: CaMeL (Debenedetti et al., 2025) fixes the control flow from the trusted user query and enforces capability-based policies outside the model. Detection defenses run a classifier on untrusted inputs, such as PromptGuard (Wan et al., 2024; Chennabasappa et al., 2025), whose robustness…
Figure 2 of the paper
Figure 2. Output-distribution drift on benign inputs. SFT and DPO shift the model’s output dis￾tribution away from the base model, while self-distillation keeps it close. Details are in Section B.1. where H contains all evaluated answer prefixes. We also report top-1 agreement, the fraction of positions where the two models assign the highest probability to the same next token. The benign￾set construction and full measurement protocol are detailed in Section B.1. To isolate the effect of the objective from that of the data, we evaluate SFT, DPO, and the self￾distillation objective used by…
Figure 3 of the paper
Figure 3. Behavioral drift on a benign tool-use task. The base model completes the task, while the defended model stops at the tool-guided step and defers it to the user. This failure pattern occurs in both prior training-based defenses we study. Additional examples are in Section B.2. 5.1 STAGE 1: SELF-GENERATION Stage 1 uses the frozen model pθ0 in three roles: generating a scenario, solving and verifying it, and generating an attack. These roles are executed as independent model calls, with no model state carried between them. Scenario generation. The base model generates a small executable
Figure 4 of the paper
Figure 4. Message feed before and after prompt sandwiching.
Figure 5 of the paper
Figure 5. Message feed before and after spotlighting with delimiting.
Figure 6 of the paper
Figure 6. Message feed before and after filtering a tool response with Prompt Guard 2.
Figure 7 of the paper
Figure 7. Per-block hidden-state changes over 88 AgentDojo pairs (Gemma-4-12B). Panels 1, 2,

Figures are the authors', reproduced from the paper.

Cited by 1 Pith paper

Reviewed papers on Pith that cite this one. The full citation record

  1. PROVISO: Provenance-Informed Action Selection for Secure LLM Agents cs.AI · Oct 2026

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment