ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Zhongyuan Peng, Dan Huang, Chuyu Zhang, Caijun Xu, Changyi Xiao, Shibo Hong, David Lo, Lin Qiu, Xuezhi Cao, Jiyuan He, Yixin Cao
• Venue: arXiv: cs.AI
• Published: 2026-07-23
• Collected: 2026-07-24
• URL: http://arxiv.org/abs/2607.21217v1
• PDF: https://arxiv.org/pdf/2607.21217v1
• DOI: UNKNOWN

Plain-Language Brief

The paper introduces a new benchmark called ICAE-Bench for evaluating coding agents in interactive project building settings. This benchmark aims to test the ability of agents to transform incomplete product intent into working software by simulating dynamic paradigms with an automated User Agent.

What the Document Says

• The paper discusses a new benchmark called ICAE-Bench for evaluating coding agents.
• ICAE-Bench is designed to test agents in interactive project building settings.
• It tests the ability of agents to transform incomplete product intent into working software.
• The benchmark simulates dynamic paradigms with an automated User Agent.
• Each task derives ambiguity from a precise real open-source repository.
• ICAE-Bench ensures high-quality and reproducible user simulation through User Agent Data.
• It uses standardized black-box tests together with multi-dimensional diagnostics.

Key Concepts Mentioned

• coding agents
• interactive project building
• ICAE-Bench
• user agent
• open-source repository

Claims Made by the Document

• Existing benchmarks do not fully catch up with the shift in what coding agents are expected to do.
• ICAE-Bench is designed to evaluate coding agents under interactive project-building settings.

Evidence Used

• The text mentions that existing benchmarks focus on static, fully specified tasks.
• The paper states that ICAE-Bench introduces a benchmark for evaluating coding agents.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

The recent emergence of vibe-coding workflows is changing what coding agents are expected to do. Instead of merely completing code under fully specified instructions, agents are increasingly expected to transform incomplete product intent into working software by combining various abilities including planning, requirement clarification, tool use, debugging, and repository-level construction. Yet existing benchmarks have not fully caught up with this shift, evaluating agents on static, fully specified tasks. In this paper, we introduce ICAE-Bench, a benchmark for evaluating coding agents under interactive project-building settings. The basic idea is to start from a fuzzy product requirement, simulating the dynamic paradigm with an automated User Agent. To make this setting both realistic and evaluable, ICAE-Bench introduces three key designs. First, to avoid the ambiguity of unconstrained fuzzy requirements, each task derives ambiguity from a precise real open-source repository with executable behavior. Second, to ensure high-quality and reproducible user simulation, ICAE-Bench grounds interaction through User Agent Data, allowing the User Agent to reveal hidden constraints without inventing new requirements or leaking implementation artifacts. Third, to evaluate open-ended repositories fairly, ICAE-Bench uses standardized black-box tests together with multi-dimensional diagnostics, including functional correctness, semantic and API similarity, structural fidelity, design quality, and interaction quality.