Agent Retrieval Bench

What is Agent Retrieval Bench?

File-level retrieval benchmark for coding agents, covering four positive tasks (code2test, comment2context, trace2code, edit2ripple) and a selective-retrieval…

Released

2026-07-27

Evaluates

Agents, Information retrieval, Language & Knowledge, Software & AI Compute

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.24882

Agent Retrieval Bench paper and code

• Paper https://arxiv.org/abs/2607.24882
• Code https://github.com/eyuansu62/agent-retrieval-bench

Which sources cite Agent Retrieval Bench?

• Agent Retrieval Bench

Related Agents, Information retrieval, Language & Knowledge, Software & AI Compute benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• Active-SWE
• ActiveSciBench