In the news
Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories
arXiv cs.AI · Published · 3 min read
In 30 seconds
- What happened
- Researchers found that embedding models fail to retrieve items with matching structure but different wording, instead matching on surface-level text similarity across mathematics and agent tasks.
- Why it matters
- Engineers building retrieval systems should care when deploying embeddings for semantic search where paraphrasing or structural variation matters more than lexical overlap.
- Watch out
- LLM rerankers recover some performance but show domain-dependent gains; mathematics recovery partly reflects memorization rather than true structural understanding of problems.
- agent
- retrieval
- embedding
- eval
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.