DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows

arXiv:2608.26546 · cs.AI, cs.CL · Submitted 2026-08-27 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-08-27

Updated: 2026-08-27

Code: https://github.com/NousResearch/hermesagent

Terminology

• Benchmark — 40× in this paper · explained in 2 episodes
• Robustness — 11× in this paper · explained in 5 episodes
• Benchmarking — 10× in this paper · explained in 4 episodes
• Content Generation — 10× in this paper
• Verification — 7× in this paper · explained in 2 episodes
• Document Editing — 6× in this paper
• AI Agents — 5× in this paper · explained in 2 episodes
• Trace — 5× in this paper · explained in 2 episodes
• APEX — 4× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Document Reading — 4× in this paper
• Failure Modes — 4× in this paper · explained in 3 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• Web Retrieval — 3× in this paper
• Aggregation — 2× in this paper · explained in 1 episode
• Fidelity — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Data Provenance — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Provenance — 1× in this paper · explained in 4 episodes

Sources

• SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments
• WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• How Benchmarks Mis-Score Computer-Use Agents
• EnvBench: A Benchmark for Automated Environment Setup
• GLM-5: from Vibe Coding to Agentic Engineering
• OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation
• CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments
• Kimi K3: Open Frontier Intelligence
• ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
• ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
• SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
• ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
• Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?
• WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting
• Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
• Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
• APEX-Agents
• FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection