# Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluation

arXiv: https://arxiv.org/abs/2602.11224 · HTML: https://mlsanity.com/paper/2602.11224/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 71 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 8 of 8)

- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers](https://mlsanity.com/paper/2508.20453/) (2025)
- [MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers](https://mlsanity.com/paper/2508.14704/) (2025)
- [Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling](https://mlsanity.com/paper/2509.26553/) (2025)
- [A Framework for Testing and Adapting REST APIs as LLM Tools](https://mlsanity.com/paper/2504.15546/) (2025)

## Built on by (most cited first, 13 of 13)

- [ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces](https://mlsanity.com/paper/2604.05172/) (2026)
- [VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills](https://mlsanity.com/paper/2606.26524/) (2026)
- [MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents](https://mlsanity.com/paper/2605.06334/) (2026)
- [OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents](https://mlsanity.com/paper/2608.05013/) (2026)
- [Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments](https://mlsanity.com/paper/2609.37315/) (2026)
- [Where Reliability Lives: Experimental Localisation of Behavioural Properties in an Agent System](https://mlsanity.com/paper/2609.03192/) (2026)
- [Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents](https://mlsanity.com/paper/2609.05261/) (2026)
- [CityPlanner: A Sandbox Agent for Executable Urban Planning](https://mlsanity.com/paper/2609.09578/) (2026)
- [Do Not Restart: Residual Completion for Stateful Agent Handoffs](https://mlsanity.com/paper/2609.13800/) (2026)
- [Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races](https://mlsanity.com/paper/2609.29522/) (2026)
- [Hearsay: Can an Auditor Trust the Record a Deployed Agent Harness Writes?](https://mlsanity.com/paper/2609.32495/) (2026)
- [One Readout, Many Repairs: Diffusion-Guided Hierarchical Search for Tool-Agent Repair](https://mlsanity.com/paper/2609.34879/) (2026)
- [Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents](https://mlsanity.com/paper/2610.04375/) (2026)

## Abstract (arXiv)

We present Agent-Diff, a novel benchmarking framework for evaluating agentic Large Language Models (LLMs) on real-world productivity software API tasks via code execution. Agentic LLM performance varies due to differences in models, external tool access, prompt structures, and agentic frameworks. Benchmarks must make fundamental trade-offs between a sandboxed approach that controls for variation in software environments and more ecologically valid approaches employing real services. Agent-Diff attempts to capture the desirable features of both of these approaches by including access to the real API interfaces for software services while sandboxing the environment in which calls are made, processed, and evaluated. This approach relies on two key innovations. The first is a novel state-diff contract, which separates process from outcome - rather than fuzzy trace or parameter matching, we define task success as whether the expected change in environment state was achieved. The second is a novel sandbox built on containerized replicas of enterprise APIs, allowing all models to interact with the same service interfaces through code execution. This enables controlled evaluation against a common set of state-diff contracts while preserving the structure of real-world API interaction. Using the Agent-Diff framework, we provide benchmarks for nine LLMs across 224 tasks utilizing enterprise software workflows. In addition, we evaluate the robustness of the framework with ablation experiments to assess the contribution of access to API documentation on benchmark performance. Code and data: https://github.com/agent-diff-bench/agent-diff.