Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.34634

AgentProofBench: Benchmarking Reusable Verifiers for Web Agents

Jingjie Ning·Xueqi Li·Yi Lu·Yibo Kong
View original source ↗Read source document ↗Export metadata ↓

Abstract

Reusable Web-agent verification requires a rule to follow changing requirements and support subsequent execution. We introduce AgentProofBench, which connects paired tests of a frozen acceptance rule to execution from identical saved openings. The resource spans 97 tasks, 79 families, and four Web services. Experiments with DeepSeek Flash/Pro establish two linked measurements. Across 48 families, complete-panel and decision-replay tests retain 82/96 Flash and 79/96 Pro source programs; paired reuse-rebuild BA intervals are [-5.47, 1.57] and [-10.16, 0.00] percentage points. Across 22 execution families, deployment-state panel correctness separates program assignments whose two saved openings are both delivered correctly: 32/33 assignments with error-free panels, versus 1/11 with panel errors. All reference-defined program-gate regressions and withheld deliveries occur in the latter group. Neutral continuation attains the highest correct delivery under the tested generic feedback, providing a concrete baseline for measuring the value added by a gate. Released instructions, states, programs, reference rules, and trajectories connect each test failure to its execution consequences. AgentProofBench makes reusable verification assessable at both the requirement and policy levels.

Explore related subjects

cs.MAcs.AIcs.SE

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Jingjie Ning, Xueqi Li, Yi Lu, Yibo Kong. 2026-10-25. AgentProofBench: Benchmarking Reusable Verifiers for Web Agents. https://arxiv.org/abs/2610.34634

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

OpenAgenet / OAN White Paper: Open Infrastructure for Trusted Agent Interconnection

OpenAgenet (OAN) is an open infrastructure project for trusted Agent interconnection across independently operated networks. It addresses the verification of resource identity, governance state, discovery authorization, and freshness before interaction. OAN combines decentralized identifiers (DIDs), verifiable credentials (VCs), and on-chain infrastructure governance with a routing-aware did:oan registration and discovery model. Registrars verify onboarding evidence; the Root service accepts resource identity versions and publishes verifiable packages; authorized Discovery nodes return signed results within their governed scope. Root also governs the semantic tag tree shared by registration and discovery. Public DID Documents and credentials remain separate from local OAN Identity signing material and from controller authorization. Skill, Runtime, Sidecar, and Gateway integration paths allow existing Agents to adopt this identity model progressively, including through the Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocol, while retaining their native task and workflow semantics. Prototype evaluation and a public pilot support examination of the trust lifecycle and its operational bottlenecks. This white paper presents the architecture, governance model, ecosystem adoption paths, and standardization opportunities for OAN as a shared identity and trust infrastructure for heterogeneous Agent resources.

cs.MA↗
arXiv2026

OpenAgenet / OAN Yellow Paper: Technical Architecture for Trust-Governed Resource Identity and Discovery

This yellow paper specifies the technical architecture and verification semantics of OpenAgenet (OAN), a protocol-neutral trust layer for heterogeneous Agent resources. The design combines did:oan decentralized identifiers (DIDs), verifiable credentials (VCs), on-chain infrastructure governance, and Root-verified resource packages. It defines the objects and lifecycle transitions that connect subject-control verification, Registrar admission, Root acceptance, authorized Discovery, and signed invocation. Infrastructure authorization requires both active governance state and a valid Root-issued credential; resource discovery additionally requires package integrity, current-version state, and authorized-domain coverage. Local OAN Identity signing material remains separate from public protocol objects. Integration profiles carry resource identity into the Model Context Protocol (MCP) and Agent-to-Agent (A2A) protocol through Skill, Runtime, Sidecar, and Gateway interfaces without redefining native task semantics. The paper distinguishes protocol requirements from implementation choices and sets out security properties, persistence and recovery expectations, and conformance criteria. Together, these rules provide a technical basis for independently implemented registration, discovery, and identity-protected interaction within an OAN trust domain.

cs.MA↗
arXiv2026

Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems

Large language model (LLM)-based multi-agent systems (MAS) rely on role-specific prompts and execution models to solve complex tasks collaboratively. However, prompt optimization typically keeps model assignments fixed, leaving differences in role requirements and their associated inference costs outside the search. We present UniMASO, a Unified framework for heterogeneous Multi-Agent System Optimization through the joint adaptation of prompts and model assignments. UniMASO evaluates candidate updates through local, downstream, and global feedback, using cost-aware Pareto search to retain useful quality-cost trade-offs. Topology-aware co-evolution then coordinates these updates according to agent roles and dependencies. Cross-level trajectory memory further supplies historical successes and failures to guide subsequent optimization. Experiments on five benchmarks and five execution topologies show that UniMASO achieves competitive task performance at substantially lower deployment cost than the strongest homogeneous configurations. Under centralized execution, it improves the average score from 69.79 to 70.40 while reducing token-weighted deployment cost by 85.2% relative to DeepSeek-V4-Pro with MASPO. These results support joint prompt-model adaptation as an effective approach to efficient multi-agent collaboration. The code is available at https://github.com/Achilles008/UniMASO_main.

cs.MA↗