Problem
Research questions and friction points this paper is trying to address.
data discovery
autonomous agents
task-specific utility
budget constraints
trustworthy feedback
Guixu: Valuation-Driven Data Discovery for Autonomous AI Agents with On-Chain Attestation
🤖 AI Summary
This work proposes a valuation-driven data discovery system tailored for autonomous AI agents, addressing key limitations of existing approaches that rely primarily on keyword-based retrieval and lack task-aware data valuation, budget-constrained optimization, and trustworthy feedback mechanisms. The system introduces a three-stage, task-aware valuation pipeline that integrates proxy label propagation, multi-round knapsack optimization, and an on-chain verifiable data marketplace to enable efficient, credible, and budget-sensitive data acquisition. By unifying task utility assessment, cost-effectiveness optimization, and blockchain-based verification for the first time, the framework supports end-to-end automation—from natural language task specifications to multi-source data search, valuation, and verifiable transactions—significantly enhancing both relevance and trustworthiness in data discovery.
📝 Abstract
Autonomous agents increasingly rely on external data to complete downstream tasks such as model training and decision support. However, existing data discovery systems remain largely retrieval-oriented: they surface candidate datasets from heterogeneous sources, but provide limited support for estimating task-specific utility, selecting cost-effective datasets under budget constraints, or incorporating trustworthy feedback from prior usage. This paper presents Guixu, a valuation-driven data discovery system for autonomous agents. Guixu employs a three-phase valuation pipeline with proxy-label propagation and multi-round knapsack optimization for task-aware data valuation. Guixu integrates agentic payment protocol to enable budget-constrained data procurement workflows. Guixu leverages on-chain data market and attestation signals for verifiable data discovery. Our demonstration highlights how Guixu enables an agent to move beyond keyword-based dataset retrieval toward task- and budget-aware, trustworthy data discovery and procurement. Attendees can interactively explore the full workflow, from NL task specification and multi-source search to data valuation and verifiable transaction feedback.
Innovation
Methods, ideas, or system contributions that make the work stand out.
valuation-driven data discovery
autonomous AI agents
on-chain attestation
budget-constrained procurement
proxy-label propagation
🔎 Similar Papers
No similar papers found.
