ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces

• URL: http://arxiv.org/abs/2604.05172v2
• Date: Wed, 08 Apr 2026 09:27:21 GMT
• Title: ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
• Abstract summary: Large language model (LLM) agents are increasingly deployed to automate productivity tasks.<n>Existing benchmarks rely on simplified environments and fail to capture realistic, multi-service environments.<n>We introduce ClawsBench, a benchmark for evaluating and improving LLM agents in realistic productivity settings.
• Score: 17.202580606345666
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is risky due to potentially irreversible changes. Existing benchmarks rely on simplified environments and fail to capture realistic, stateful, multi-service workflows. We introduce ClawsBench, a benchmark for evaluating and improving LLM agents in realistic productivity settings. It includes five high-fidelity mock services (Gmail, Slack, Google Calendar, Google Docs, Google Drive) with full state management and deterministic snapshot/restore, along with 44 structured tasks covering single-service, cross-service, and safety-critical scenarios. We decompose agent scaffolding into two independent levers (domain skills that inject API knowledge via progressive disclosure, and a meta prompt that coordinates behavior across services) and vary both to measure their separate and combined effects. Experiments across 6 models, 4 agent harnesses, and 33 conditions show that with full scaffolding, agents achieve task success rates of 39-64% but exhibit unsafe action rates of 7-33%. On OpenClaw, the top five models fall within a 10 percentage-point band on task success (53-63%), with unsafe action rates from 7% to 23% and no consistent ordering between the two metrics. We identify eight recurring patterns of unsafe behavior, including multi-step sandbox escalation and silent contract modification. We release the trajectories and future dataset at https://clawsbench.com.

Related papers

• TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents [41.82249291285459]
  TRACE iteratively improves a skill-based agent's behavioral knowledge without modifying model weights.<n>On GPT-5.5, TRACE improves consistency (Pass3) by 34.6 points, from 59.9% to 94.5%, while shrinking the gap between potential and reliable performance to just 4.0 points.<n>These results show that TRACE converts high model potential into stable, consistent performance gain.
  arXiv  Detail & Related papers  (2026-08-24T04:36:03Z)
• ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents [23.994328225666663]
  Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.<n>We define behavioral safety and introduce ActBench, a benchmark that evaluates such behavior risk from execution trajectories rather than final responses.<n>ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and 48 web-service APIs.
  arXiv  Detail & Related papers  (2026-08-10T11:45:03Z)
• ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents [61.184954205350984]
  ClawArena-Team is a benchmark of 41 multi-turn, multimodal, multi-agent scenarios spanning 258 evaluation rounds and 72 staged updates.<n>All scoring is execution-based with no LLM judge: an overall score -- the Subagent-Management Score (SMS) -- multiplies task correctness by a least-privilege and modality-routing factor.
  arXiv  Detail & Related papers  (2026-06-30T06:06:08Z)
• AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations [0.0954904463032233]
  Indirect prompt injection in tool-use agents is a concrete production threat.<n>AGENTREDBENCH is a benchmark of 215 subtle underspecified authorization scenarios.<n>AGENTREDGUARD is a guard trained on an integration-diverse corpus of adversarial tool-response content.
  arXiv  Detail & Related papers  (2026-06-01T13:34:24Z)
• Orchard: An Open-Source Agentic Modeling Framework [124.68499958175111]
  We present Orchard, an open-source framework for scalable agentic modeling.<n>At its core is Orchard Env, a lightweight environment service providing reusable primitives for sandbox lifecycle management.<n>On top of Orchard Env, we build three agentic modeling recipes.
  arXiv  Detail & Related papers  (2026-05-14T16:35:12Z)
• MEME: Multi-entity & Evolving Memory Evaluation [76.57263966646404]
  MEME defines six tasks spanning the full space defined by the multi-entity and evolving axes.<n> evaluating six memory systems spanning three memory paradigms on 100 controlled episodes.<n>We find that all systems collapse on dependency reasoning under the default configuration.
  arXiv  Detail & Related papers  (2026-05-12T17:55:10Z)
• ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents [77.22389710754452]
  We introduce bench, a benchmark for coworker agents built around multi-turn multi-day tasks.<n>The current release contains 100 tasks across 13 professional scenarios, executed against five stateful sandboxed services.<n>The strongest model reaches 75.8 weighted score, but the best strict Task Success is only 20.0%, indicating that partial progress is common.
  arXiv  Detail & Related papers  (2026-04-26T16:05:02Z)
• ClawArena: Benchmarking AI Agents in Evolving Information Environments [61.664633997138004]
  ClawArena is a benchmark for evaluating AI agents in evolving information environments.<n>Each scenario maintains a complete hidden ground truth while exposing the agent only to noisy, partial, and sometimes contradictory traces.<n> evaluation is organized around three coupled challenges: multi-source conflict reasoning, dynamic belief revision, and implicit personalization.
  arXiv  Detail & Related papers  (2026-04-05T17:55:23Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Multimodal Safety Evaluation in Generative Agent Social Simulations [43.972551727499116]
  We introduce a reproducible simulation framework for evaluating agents along three dimensions.<n>We show that agents often fail to align local revisions with global safety, reaching only a 55 percent success rate in correcting unsafe plans.<n> Notably, 45 percent of unsafe actions were accepted when paired with misleading visuals, showing a strong tendency to overtrust images.
  arXiv  Detail & Related papers  (2025-10-09T02:42:57Z)
• SCUBA: Salesforce Computer Use Benchmark [63.66753028386581]
  SCUBA is a benchmark designed to evaluate computer-use agents on customer relationship management ( CRM) within the Salesforce platform.<n> SCUBA contains 300 task instances derived from real user interviews, spanning three primary personas, platform administrators, sales representatives, and service agents.<n>We benchmark a diverse set of agents under both zero-shot and demonstration-augmented settings.
  arXiv  Detail & Related papers  (2025-09-30T16:48:49Z)
• GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging [41.754784344572286]
  We release GitTaskBench, a benchmark for evaluating code agents in real-world scenarios.<n>Each task pairs a relevant repository with an automated, human-curated evaluation harness.<n>We also propose the alpha-value metric to quantify the economic benefit of agent performance.
  arXiv  Detail & Related papers  (2025-08-26T12:48:05Z)
• 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)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)
• SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents [58.65256663334316]
  We present SafeAgentBench -- the first benchmark for safety-aware task planning of embodied LLM agents in interactive simulation environments.<n>SafeAgentBench includes: (1) an executable, diverse, and high-quality dataset of 750 tasks, rigorously curated to cover 10 potential hazards and 3 task types; (2) SafeAgentEnv, a universal embodied environment with a low-level controller, supporting multi-agent execution with 17 high-level actions for 9 state-of-the-art baselines; and (3) reliable evaluation methods from both execution and semantic perspectives.
  arXiv  Detail & Related papers  (2024-12-17T18:55:58Z)
• Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models [33.1538965735133]
  Cybench is a framework for specifying cybersecurity tasks and evaluating agents on those tasks.<n>We include 40 professional-level Capture the Flag (CTF) tasks from 4 distinct CTF competitions.<n>We construct a cybersecurity agent and evaluate 8 models: GPT-4o, OpenAI o1-preview, Claude 3 Opus, Claude 3.5 Sonnet, Mixtral 8x22b Instruct, Gemini 1.5 Pro, Llama 3 70B Chat, and Llama 3.1 405B Instruct.
  arXiv  Detail & Related papers  (2024-08-15T17:23:10Z)

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.