ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2607.14890· 20 results

cs.SEcs.AIcs.CRRecentJun 2, 2026

Proof-Carrying Agent Actions: Model-Agnostic Runtime Governance for Heterogeneous Agent Systems

Zexun Wang

The paper proposes Proof-Carrying Agent Actions (PCAA), a runtime-neutral governance model that uses action certificates to consistently track and authorize high-risk actions across diverse and hetero…

View →
cs.CRcs.AIRecentApr 28, 2026

From CRUD to Autonomous Agents: Formal Validation and Zero-Trust Security for Semantic Gateways in AI-Native Enterprise Systems

Ignacio Peyrano

The paper proposes a Semantic Gateway and a Zero-Trust security model to formally validate and secure autonomous AI agents operating in enterprise systems, achieving a 100% discovery rate of unauthori…

View →
cs.CRcs.AIRecentMay 7, 2026

From Specification to Deployment: Empirical Evidence from a W3C VC + DID Trust Infrastructure for Autonomous Agents

Lars Kersten Kroehl

The paper introduces MolTrust, a production-deployed trust infrastructure built on W3C standards (VCs and DIDs) that provides a verifiable, multi-layered authorization framework for autonomous AI agen…

View →
cs.CRRecentMay 20, 2026

An Evidence-driven Protocol for Trustworthy CI Pipelines

Fernando Castillo, Eduardo Brito, Pille Pullonen-Raudvere, Sebastian Werner +1 more

The paper proposes an evidence-driven protocol combining Deterministic Build Systems and Trusted Execution Environments to provide cryptographically verifiable guarantees of software artifact integrit…

View →
cs.CRcs.AIcs.ETRecentApr 27, 2026

Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing

Antony Rowstron

The paper proposes Agentic Witnessing, a TEE-enabled framework that allows external verifiers to audit the qualitative properties of private datasets by querying an LLM-based auditor without accessing…

View →
cs.CRcs.LOcs.MARecentMay 19, 2026

Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks

Ravi Kiran Kadaboina

Pramana introduces a standardized, protocol-level wire format for autonomous agent outputs, ensuring that every consequential claim is accompanied by a verifiable artifact that can be re-executed by a…

View →
cs.CRcs.LGRecentApr 24, 2026

Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems

Jun He, Deying Yu

The paper introduces Sovereign Agentic Loops (SAL), a control-plane architecture that decouples LLM reasoning from system execution to enhance safety and reliability in real-world AI agents.

View →
cs.AIRecentMay 27, 2026

ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research

Yihan Xia, Taotao Wang

ResearchLoop introduces an evidence-gated control plane to manage and audit the state of AI-assisted computational research, mitigating the risk of unverified claims.

View →
cs.LOcs.CRcs.FLRecentMar 20, 2026

Agentproof: Static Verification of Agent Workflow Graphs

Melwin Xavier, Vaisakh M A, Melveena Jolly, Midhun Xavier

Agentproof is a system that provides static, pre-deployment verification of safety properties in agent workflow graphs by automatically extracting a unified graph model and applying structural and tem…

View →
cs.CRcs.AIRecentJun 3, 2026

From Agent Traces to Trust: Evidence Tracing and Execution Provenance in LLM Agents

Yiqi Wang, Jiaqi Zhang, Taotao Cai, Zirui Liu +5 more

This survey provides a systematic framework and taxonomy for evidence tracing and execution provenance in LLM agents, addressing the difficulty of verifying and auditing complex agent behaviors.

View →
cs.CYcs.AIeess.SYTheoreticalRecentJul 17, 2026

A Methodology for Auditable Trustworthiness Levels in AI Lifecycle Governance

Andrea Ferrario

The paper proposes a methodology for auditable trustworthiness levels in AI governance with a formal framework and a lightweight procedure.

View →
cs.CRcs.AIRecentMay 7, 2026

LoopTrap: Termination Poisoning Attacks on LLM Agents

Huiyu Xu, Zhibo Wang, Wenhui Zhang, Ziqi Zhu +3 more

The paper introduces LoopTrap, an automated red-teaming framework that demonstrates how malicious prompts can poison the termination judgment of LLM agents, causing unbounded computation.

View →
cs.CRcs.AIcs.MARecentMay 1, 2026

Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes

Alfredo Metere

The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…

View →
cs.CRRecentMar 30, 2026

Attesting LLM Pipelines: Enforcing Verifiable Training and Release Claims

Zhuoran Tan, Jeremy Singer, Christos Anagnostopoulos

The paper proposes an attestation-aware promotion gate to mitigate supply-chain risks in LLM pipelines by cryptographically verifying and enforcing claims about training and release artifacts before d…

View →
cs.AIcs.CRRecentMay 6, 2026

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use

Chenglin Yang

AgentTrust is a novel runtime safety layer that intercepts and evaluates AI agent tool calls before execution, achieving high accuracy in detecting unsafe actions across complex and obfuscated scenari…

View →
cs.CRcs.AIRecentMay 14, 2026

MemLineage: Lineage-Guided Enforcement for LLM Agent Memory

Ciyan Ouyang, Rui Hou

MemLineage introduces a novel, cryptographically-backed defense mechanism that enforces a chain-of-custody for LLM agent memory, preventing untrusted or poisoned state from justifying sensitive action…

View →
cs.CRcs.AIRecentMar 19, 2026

Agent Control Protocol: Admission Control for Agent Actions

Marcelo Fernandez

The paper introduces Agent Control Protocol (ACP), a stateful temporal admission control mechanism that enforces behavioral properties over execution traces to prevent harmful patterns from individual…

View →
cs.CRcs.AIcs.GTRecentApr 24, 2026

Reconstructive Authority Model: Runtime Execution Validity Under Partial Observability

Marcelo Fernandez - TraslaIA

The paper introduces the Reconstructive Authority Model (RAM), a novel framework that proves execution validity by assessing state coverage rather than just state integrity, showing that existing atte…

View →
cs.SEcs.AIcs.CYTheoreticalRecentJul 3, 2026

CAGE-1: Control, Assurance, and Governance Evaluation for Enterprise Agentic AI

Roopam W. Sure

This paper introduces CAGE-1, an evaluation framework for deciding the readiness of enterprise agents for deployment, focusing on control, assurance, and governance.

View →
cs.CRcs.AIcs.PLRecentMay 1, 2026

Certified Purity for Cognitive Workflow Executors: From Static Analysis to Cryptographic Attestation

Alan L. McCann

The paper introduces a certified purity architecture that strengthens governance in cognitive workflow systems by replacing insufficient runtime checks with cryptographically attested structural guara…

View →