WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

• URL: http://arxiv.org/abs/2608.03499v1
• Date: Tue, 04 Aug 2026 11:42:26 GMT
• Title: WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks
• Abstract summary: We introduce WeClawArena, an auditable benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces.<n>WeClawArena targets collaborative tool-use tasks in which personal workspaces serve as both operational tools and personal constraints.
• Score: 8.407647753724103
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners. Existing agent benchmarks study tool use and collaboration, but they do not provide an end-to-end sandbox for verifiable cross-user agent collaboration with realistic user digital workspaces or test how harmful actions can travel through the human-centered agent network. We introduce WeClawArena, an auditable benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces. WeClawArena targets collaborative tool-use tasks in which personal workspaces serve as both operational tools and personal constraints. The benchmark contains 124 base tasks across six cross-user task domains and expands them into 620 scenario variants, with one benign control and four attack-vector variants per base task. The sandbox records peer messages, tool calls, resource operations, governed decisions, and final workspace states. WeClawArena reports utility and attack success rate separately and audits attack success from bounded runtime evidence, supporting diagnosis of task breakdown, privacy leakage, poisoned evidence, and invalid authority paths.

Related papers

• DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows [69.12339622053588]
  We introduce DuMateBench, a real-session benchmark reconstructed from anonymized and privacy-screened user sessions.<n>The resulting benchmark comprises 200 tasks spanning 8 broad scenarios and 17 fine-grained capability categories.<n>We execute these tasks in isolated Docker containers injected with three forms of real-world environmental complexity: Insufficient, Unstable, and Noisy.
  arXiv  Detail & Related papers  (2026-08-27T02:36:23Z)
• Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction [57.138342889101345]
  Tencent WorkBuddy Bench is a multi-domain evaluation suite for coding agents.<n>This report documents its construction methodology, scoring protocol, and a cross-model leaderboard.
  arXiv  Detail & Related papers  (2026-07-23T04:34:06Z)
• Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing [4.508726112104009]
  Large language model (LLM) agents are starting to take on routine work in high-performance computing.<n>This paper defines the threat model in the HPC setting, identifies attack surfaces created by schedulers, shared storage, multi-project accounts, and scientific, and examines where current controls fall short.
  arXiv  Detail & Related papers  (2026-07-20T20:16:02Z)
• CONTRA: Red-Teaming Configurations of Personalizable Agents [31.01865239234458]
  We explore the interplay between agent configuration and the risk of executing dangerous actions without explicit instruction.<n>We propose CONfiguration Tree-search for Red-teaming Agents (CONTRA), an LLM-assisted tree-search algorithm.<n>In a large-scale analysis, we find that 75.1% of skills have at least one configuration resulting in the execution of a malicious action.
  arXiv  Detail & Related papers  (2026-07-03T11:34:27Z)
• Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity? [54.701199583505144]
  Cross-application access creates a privacy risk that has been largely overlooked.<n>We introduce AgentCIBench, an evaluation harness that turns this risk into executable, deterministically scored scenarios.<n>We evaluate 15 frontier agents and find a surprisingly high failure rate.
  arXiv  Detail & Related papers  (2026-06-22T11:36:58Z)
• Collaborative Human-Agent Protocol (CHAP) [0.18352113484137622]
  This paper presents CHAP, the Collaborative Human-Agent Protocol.<n>Under CHAP, the override that used to vanish into a chat thread becomes a structured event carrying a diff, a rationale, and a content hash.<n>The protocol achieves this through a small Core (workspaces, participants, tasks, artefacts, and an append-only evidence log) together with composable profiles that add review, modes, routing, deliberation, handoff, identity, signatures, and transparency-backed audit as deployments require them.
  arXiv  Detail & Related papers  (2026-06-08T17:11:42Z)
• AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions [78.49000936275773]
  We introduce AgentHijack, a benchmark designed to evaluate the robustness of computer-use agents under common corruptions.<n>We evaluate a variety of desktop tasks that utilize MLLM-based agents and discover that even minor instances of corruption can result in substantial performance degradation.<n>We propose AgentHijack-Agent, a framework that integrates an action generator with enhanced grounding capabilities and an onlooker responsible for behavior summarization and environment checking.
  arXiv  Detail & Related papers  (2026-05-25T11:09:22Z)
• ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation [33.44625630134376]
  We argue that the next frontier for AI agents lies not in stronger individual capability, but in the digitization of human collaborative relationships.<n>Each user owns a permanently bound agent system that collaborates on the owner's behalf, forming a network whose nodes are humans rather than agents.<n>ClawNet is an identity-governed agent collaboration framework that enforces identity binding and authorization verification through a central orchestrator.
  arXiv  Detail & Related papers  (2026-04-21T08:15:05Z)
• ALARA for Agents: Least-Privilege Context Engineering Through Portable Composable Multi-Agent Teams [0.0]
  We introduce a declarative context-agent-tool (CAT) data layer expressed through interrelated files that scope each agent's tool access and context to the minimum its role requires.<n>Because the system parses and enforces these files structurally, modifying an agent's tool list produces a guaranteed behavioral change rather than a suggestion the model may or may not follow.<n>We evaluate 22 locally-hosted models from 0.6B to 35B parameters across 115 practical tasks spanning file operations, web search, multi-step scripting, tool chaining, and multi-agent delegation.
  arXiv  Detail & Related papers  (2026-03-20T18:00:09Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• Kaleidoscopic Teaming in Multi Agent Simulations [75.47388708240042]
  We argue that existing red teaming or safety evaluation frameworks fall short in evaluating safety risks in complex behaviors, thought processes and actions taken by agents.<n>We introduce new in-context optimization techniques that can be used in our kaleidoscopic teaming framework to generate better scenarios for safety analysis.<n>We present appropriate metrics that can be used along with our framework to measure safety of agents.
  arXiv  Detail & Related papers  (2025-06-20T23:37:17Z)
• Learning to Use Tools via Cooperative and Interactive Agents [58.77710337157665]
  Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. We propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. Our experiments on three datasets show that the LLMs, when equipped with ConAgents, outperform baselines with substantial improvement.
  arXiv  Detail & Related papers  (2024-03-05T15:08:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.