The authors built SERBench from 500 held-out coding-agent states across 45 repositories.
Coding agents retrieve better by targeting missing evidence sets
A state-aware retrieval method assembled complete evidence for coding decisions more often than passage-by-passage ranking baselines.
Industry
Zhexi Feng · Ruiyi Zhang · Yongbo Yang · Pengtao Xie
University of California San Diego
Research Digest··2 min read
Feng et al.
Why this paper
From University of California San Diego · Part of Context Engineering for Agents, now 23 papers
In one line
Retrieval for coding agents should recover a minimal set of evidence that completes what the agent still lacks, not re-rank relevant passages.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§