HadAgent: Harness-Aware Decentralized Agentic AI Serving with Proof-of-Inference Blockchain Consensus

2026-04-15

AI Summary

This work addresses the inefficiency of traditional Proof-of-Work (PoW) consensus, which consumes substantial computational resources without producing useful output, alongside the growing demand for large language model (LLM) inference that strains GPU availability. To reconcile these challenges, the paper proposes a novel Proof-of-Inference (PoI) consensus mechanism that leverages deterministic LLM inference tasks as the basis for block production. The design incorporates a three-channel block structure and a two-layer node architecture to enable fine-grained tamper resistance and efficient verification. A behavior-aware Harness layer is introduced to facilitate automatic trust evaluation and rapid isolation of malicious nodes. Experimental results demonstrate that the prototype system achieves 100% detection of tampering with zero false positives, sub-millisecond validation latency for record and hub operations, expulsion of adversarial nodes within two rounds, and promotion of honest nodes to trusted status within five rounds.

Technology Category

• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Machine Learning: Hardware-aware ML
• Multiagent Systems: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Proof-of-Work (PoW) blockchain consensus consumes vast computational resources without producing useful output, while the rapid growth of large language model (LLM) agents has created unprecedented demand for GPU computation. We present HadAgent, a decentralized agentic AI serving system that replaces hash-based mining with Proof-of-Inference (PoI), a consensus mechanism in which nodes earn block-creation rights by executing deterministic LLM inference tasks. Because verification requires only re-executing a single forward pass under identical conditions, cross-node verification operates at consensus speed. HadAgent organizes validated records into a three-lane block body with dedicated DATA, MODEL, and PROOF channels, each protected by an independent Merkle root for fine-grained tamper detection. A two-tier node architecture classifies secondary nodes as trusted or non-trusted based on historical behavior: trusted nodes serve inference results in real time through optimistic execution, while non-trusted nodes must undergo full consensus verification. A harness layer monitors node behavior through heartbeat probes, anomaly detection via deterministic recomputation, and automated trust management, creating a self-correcting feedback loop that isolates malicious or unreliable participants. Experiments on a prototype implementation demonstrate 100% detection rate and 0% false positive rate for tampered records, sub-millisecond validation latency for record and hub operations, and effective harness convergence that excludes adversarial nodes within two rounds while promoting honest nodes to trusted status within five rounds.

Problem

• Proof-of-Inference
• Decentralized AI Serving
• Blockchain Consensus
• LLM Agents
• Trust Management

Innovation

• Proof-of-Inference
• Decentralized AI Serving
• LLM Agents
• Merkle-root Channels
• Trust Management