research
The Search Agent Let Coverage Decide How Many Documents to Keep
CAS replaces fixed top-K retrieval with adaptive prediction sets and penalizes low-confidence training trajectories.
Summary
CAS replaces fixed top-K retrieval with adaptive prediction sets and penalizes low-confidence training trajectories.
The framework applies conformal methods on both sides of search-agent training: document sets expand or contract to target coverage, while answer confidence weights the GRPO objective. The preprint reports higher reasoning accuracy and fewer redundant tool calls across single- and multi-hop QA datasets.
Why it matters
CAS replaces fixed top-K retrieval with adaptive prediction sets and penalizes low-confidence training trajectories.
Limits and context
No additional limitation was separately recorded.
Key claims
CAS replaces fixed top-K retrieval with adaptive prediction sets and penalizes low-confidence training trajectories.
Evidence: source-2026-08-24-015
Sources
- arXiv preprint 2608.20771arXiv · primary research
Corrections
No corrections have been recorded for this story.