The paper introduces Verifiable Agent Insurance (VAI), a framework that lets AI agent providers commit to policy compliance through smart contracts and escrow funds on a blockchain. When a user detects a policy violation, a verifier reviews execution traces logged by the agent harness; if the violation is confirmed, the escrow is paid to the user. Experiments on three agent benchmarks show VAI detects 42.2% of violations, rising to 83.0% when agents emit explicit structured records.
arXiv:2609.37819v1 Announce Type: cross Abstract: Electronic invoices are replacing paper invoices worldwide, but today's centralized architectures leave three problems unsolved on the consumption si...
arXiv:2604. 05485v2 Announce Type: replace Abstract: LLM agents call tools, query databases, delegate tasks, and trigger external side effects.
arXiv:2608. 16402v1 Announce Type: new Abstract: Large language model-based agentic frameworks primarily optimize capability: whether an agent can reason, retrieve information, call tools, delegate work, and complete a goal.
The paper "When Agents Act Unwatched: The Reduced‑Supervision Paradox in Agentic AI" discusses how the promise that AI systems will continue acting after users stop watching creates an accountability inversion. It argues that as stepwise supervision recedes, verification shifts into the runtime infrastructure—authority, records, interrupts, outcome checks, and repair—forming what the authors call the reduced‑supervision paradox. A 63‑artifact audit across research papers and engineering sources shows that agents’ action surfaces are more visible than the mechanisms needed to hold them accountable, with tool mediation and monitoring traces appearing in 40 and 37 artifacts, while checkpoint placement, validator independence, recovery, and contestability are rarely visible. "whyItMatters":"The study highlights that observable action paths can replace accountability when verification is moved onto users after meaningful intervention is no longer possible."
As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness. In decentralized energy markets, autonomous agents may improve market utility, but may also exploit invalid physical data, create artificial liquidity, and produce unstable governance decisions.
arXiv:2607. 08681v1 Announce Type: new Abstract: As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness.
arXiv:2607. 05397v1 Announce Type: cross Abstract: Agent systems increasingly execute rather than advise.
arXiv:2606. 30970v1 Announce Type: new Abstract: Autonomous AI agents increasingly perform consequential actions on behalf of human principals, including financial transactions, external communications, and enterprise workflows.
The paper introduces Aegis, a runtime governance system for agentic AI that treats model outputs as action proposals and mediates them through a trusted decision layer before tool execution. Aegis evaluates proposals against active policy, resolves provenance server‑side, fails closed under uncertainty, and routes selected cases through a Senate‑style settlement process. In a sandbox evaluation across 6,300 rows, Aegis prevented all governed mock‑tool applications and risky side‑effect completions, preserving provenance and quorum evidence for all settled cases.
arXiv:2609.14744v2 Announce Type: replace Abstract: By acquiring compute, credentials, accounts, services, and other agents, autonomous AI agents can introduce new authority into a task. Payment, bud...
AgentXploit is a two‑role auditing system that separates repository‑level attack‑path discovery from runtime exploitation for AI agents. The Analyzer Agent traces attacker‑controlled inputs to sensitive operations and records candidate attack paths, while the Exploiter Agent turns these paths into concrete attacks and refines them using runtime feedback. The system is evaluated on AgentXploit‑Bench, a benchmark of 72 reproducible vulnerabilities across 12 open‑source AI‑agent systems, achieving 59.3% end‑to‑end success compared to 38.4% for Codex, and 79.2% attack success on AgentDojo versus 52.7% for AgentVigil.
arXiv:2608. 14074v1 Announce Type: new Abstract: AI agents increasingly act on external systems through standardized tool-calling protocols such as the Model Context Protocol (MCP), yet no infrastructure layer constrains their actions to what a principal has verifiably authorized: authorization logic lives in application code, is neither signed nor independently auditable, and the resulting logs lack evidentiary value.