arXiv:2610.01756v1 Announce Type: cross
Abstract: Decentralized agent economies increasingly build a single task from protocols that were designed and secured separately. This creates a simple proble...
By Rui Sun, Xihan Xiong, Qin Wang, Fei Gao, Zelin Li, Zehua Cheng, Jiahao Sun, Zhipeng Wang
The paper presents a formal analysis of four agent payment protocols—x402, MPP, ACP, and AP2—using the Tamarin prover. By modeling each protocol’s roles, state, and trust assumptions, the authors verify 86 cases, reproducing 46 known results and uncovering 40 new formal-consistency findings. They further validate ten findings through implementation proofs of concept, SDK/schema witnesses, and executable traces, highlighting the importance of consistent delegated authorization across all protocol stages.
By Ke Jiang, Mohan Yu, Yuan Chang, Mohit Kumar Jangid, Jianyu Niu, Cong Wang, Yinqian Zhang
arXiv:2608. 07583v1 Announce Type: cross Abstract: Multi-agent LLM systems route among model-backed advisors, yet a deployer rarely knows before shipping whether routing will help at all.
By Anchen Sun, Kaiqi Yang
arXiv:2608. 19861v1 Announce Type: new Abstract: Customer-service LLM agents must follow organizational policy when acting on a user's behalf.
By Seongjae Kang, Taehyung Yu, Sung Ju Hwang
arXiv:2605. 06738v2 Announce Type: replace-cross Abstract: Autonomous AI agents already transact at production scale -- 69,000 bots, 165 million transactions, $50 million in volume on a single marketplace -- and any party can verify a signed credential without a central service.
By Lars Kersten Kroehl
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