arXiv AI

Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs

arXiv AI
Oct 16

Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization

The paper "Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization" examines how AI agents seek approval before performing actions such as sending money or deleting files. It identifies twelve attack vectors on the approval process and evaluates them against several protocols, finding that many agent runtimes lack verifiable approval records and exhibit binding weaknesses. The authors propose a defense called ASU (Agent Step-Up), which renders a canonical approval card, requires a phone passkey, and enforces single-use execution, demonstrating strong protection against substitution, replay, and grant-stretching attacks in extensive simulations.

By Sai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargill
arXiv AI
Sep 3

ClaimReceipt: Verifying Evidence Sufficiency and Coverage in Agent Evaluations

The paper introduces ClaimReceipt, a specification and verifier that checks whether a claim in an agent evaluation can be recomputed from retained evidence (sufficiency) and whether the evidence covers the entire experiment set (coverage). Using the CR‑2 verifier on 1,392 historical records, the authors demonstrate accurate reproduction of audit verdicts, non‑redundant field groups, and zero false positives on semantic faults. In a prospective CR‑3 run, the system correctly flags missing receipts and preserves coverage when private evidence is withheld, while adding minimal overhead to inference time and transaction size.

By Peiying Zhu, Sidi Chang
arXiv AI
Oct 23

Correlated Failures of AI Approval Monitors

The paper investigates how AI approval monitors can fail together when they share a base model or poisoned input, using concepts from distributed computing to identify vulnerable monitor sets. Experiments on twelve open‑weight monitors and several closed models show that fooling a monitor into approving fraud is limited to its own evidence source, while blocking correct payments requires overcoming injection resistance. A rule that counts distinct evidence sources rather than votes reduces false rejections, and adding a rule engine that cannot be persuaded restores safety and liveness against the measured attacks.

By Luca Zanolini
arXiv AI
Nov 6

Signed but Not Safe: Requirement Integrity in Multi-Agent LLM Handoffs

The paper investigates how to preserve user‑specified requirements when enterprise AI agents hand off tasks to subagents. It compares free‑text, structured JSON, and signed requirement‑manifest handoffs, showing that signing the manifest with HMAC‑SHA256 dramatically reduces unsafe commits (from 69.4% to 9.0%) while maintaining compliance. The study also demonstrates that deterministic verification outperforms LLM‑based checking and that the main remaining risk lies in the extraction step before signing.

By Xiaobo Chen, Genliang Zhu, Ziyuan Wang, Chu Wang
arXiv AI
Aug 24

Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol

The paper introduces a framework for evaluating how large language model agents revise their success criteria after failures, defining five non‑compensatory conditions that must be met for a criterion revision to be considered valid. Using the CMB‑0.1 protocol, the authors test twelve cross‑domain scenarios across four system configurations, finding that no model trial satisfies all five conditions and highlighting specific failure modes such as zero‑state reconstruction and inadequate intervention sensitivity. They propose a more stringent trace‑anchored CMB‑0.4 protocol to better isolate and measure criterion revision in future studies.

By Guodong Xu
arXiv AI
Oct 31

PCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication

The paper introduces Proof‑Carrying Messages (PCM), a protocol that attaches verifiable evidence—Merkle log records and signed attestations—to each claim exchanged between AI agents. PCM enables receivers to evaluate claims offline, categorizing them as proven, unproven, or failed, and ensures that claims based solely on an agent’s own report can never be proven. In benchmark tests on 926 real messages, PCM accepted only 1.4% of false claims, whereas other protocols accepted many more.

By Bravish Ghosh (Cygnux Labs)
arXiv AI
Aug 19

PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance

The paper introduces PACE (Policy‑Attested Contract Execution), a framework that sits between large‑language‑model (LLM) based autonomous AI agents and on‑chain DeFi operations. PACE defines typed transaction intents, a deterministic policy verifier, and signed Policy Decision Records (PDRs) that cryptographically bind an approved intent, policy, and simulation report to the exact on‑chain execution bytes, providing replay and expiration protection. In evaluations across 40 tasks and six baselines, PACE achieves zero unsafe executions and zero false positives, outperforming unguarded agents by a large margin.

By Rabimba Karanjai (Larry), Yang Lu (Larry), Richard Williamson (Larry), Hemanth Hm (Larry), Prakhar Mehrotra (Larry), Lei Xu (Larry), Weidong (Larry), Shi
arXiv AI
Oct 1

Who Verifies the Graph? Misspecification Attacks on Causal Action Verification for Language Agents

The paper investigates how causal action verifiers, which guard language agents’ tool calls by checking identifiability against a committed action‑state graph, can be compromised through small graph misspecifications. By removing a single bidirected edge or reversing an arrowhead, the authors demonstrate that a verifier (CIVeX) that originally had zero false executions can suffer false execution rates up to 48.9%, with most of those executions being harmful and overall utility dropping dramatically. An additional attestation step that samples executions can detect these attacks with few false alarms, but it also leads to many wrongful rejections that reduce beneficial actions and incur significant experimental costs. whyItMatters":"The study shows that even minor errors in the verifier’s underlying graph can drastically undermine safety and performance, highlighting the need for robust auditing mechanisms."

By Fabio Rovai
arXiv AI
Sep 25

Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents

The paper investigates where exactly‑once semantics should be enforced for tool‑using agents—within the model, the agent harness, or the tool contract—by evaluating 25,930 episodes across nine models, three harnesses, two contract variants, and fifteen recovery conditions. Using the LIMBO sandbox, the study shows that when an immediate read‑back is available, frontier models rarely duplicate lost acknowledgements, whereas weaker models do; when read‑back is unavailable, the contract’s idempotency keys explain most duplicate behavior. The authors prove that verification‑only policies cannot guarantee exactly‑once under late commits without bounded in‑flight time, and that waiting only helps when delays are short and predictable. whyItMatters":"The findings clarify that enforcing exactly‑once semantics largely depends on the tool contract and fault type, guiding designers on where to focus reliability mechanisms for LLM agents."

By Jiapeng Li