Pollard：面向框架无关 AI 智能体控制与回放的可治理语义执行树

View PDF HTML (experimental)

Abstract:Agent frameworks can persist checkpoints, trace tool calls, and limit resource use, but these facilities often assign different identities to execution, governance, and replay. We present Pollard, a framework-independent runtime based on governed semantic execution trees. A step identity commits to canonical input, kind, attempt, and parent identity; the same tree records completion, refusal, resource settlement, and branch history. Strict replay returns a verified stored result without invoking the wrapped operation, while a transactional store coordinates reservations across concurrent workers. Under a signed deterministic freeze, two state-model replicas each executed the evaluation transitions without an invariant violation, retained-lease PostgreSQL groups were tested against exact limits, strict replay avoided external calls, and all semantic mutations were detected with no false alarms on the controls. A multi-pair framework matrix preserved reference behavior and verified the trees. A separate cost-capped hosted study exercised live provider paths, and every completed Pollard trial produced a verified tree. Together, the studies support the core mechanisms under explicit lease, boundary, and seal-custody assumptions.

Comments:	Accepted at IEEE ICTAI 2026 (short paper)
Subjects:	Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
Cite as:	arXiv:2610.16145 [cs.AI]
	(or arXiv:2610.16145v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2610.16145 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Muntaser Syed [view email]
[v1] Mon, 12 Oct 2026 04:06:47 UTC (21 KB)