Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

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

Hubert M. Pysklo, Artem Zhuravel, Patrick D. Watson

Published

Feb 11, 2026

Citations

0

Trust level

Moderate

Usefulness score

25/100 (Low)

Extraction confidence

55% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Mar 24, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Coding Tool Use

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this for comparison and orientation, not as your only source.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
25/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

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.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"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."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"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."

Quality Controls

missing

Not reported

No explicit QC controls found.

"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."

Benchmarks / Datasets

strong

Agent Diff Bench

Useful for quick benchmark comparison.

"Code and data: https://github.com/agent-diff-bench/agent-diff."

Reported Metrics

strong

Task success

Useful for evaluation criteria comparison.

"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."

Benchmarks and datasets

agent-diff-bench

Reported metrics

task success
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Coding
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
Tool Use
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Background context only

Research brief

Metadata summary

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.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • 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.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Simulation environment, Tool-use evaluation) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • 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.
  • In addition, we evaluate the robustness of the framework with ablation experiments to assess the contribution of access to API documentation on benchmark performance.

Why it matters for eval

  • 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.
  • In addition, we evaluate the robustness of the framework with ablation experiments to assess the contribution of access to API documentation on benchmark performance.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: agent-diff-bench

  • Metric reporting is present

    Detected: task success