An iterative loop of RL and filtered SFT on the agent's own rollouts improves a 7B web-search agent by a few accuracy points on multi-hop QA benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EvolveSearch: An Iterative Self-Evolving Search Agent
An iterative loop of RL and filtered SFT on the agent's own rollouts improves a 7B web-search agent by a few accuracy points on multi-hop QA benchmarks.