Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based Agents

ArXi:2606.02204v1 Announce Type: new Large language model agents achieve strong performance on text-based benchmarks but incur prohibitive inference costs, motivating the use of compact neural rerankers for action selection. We investigate whether a single lightweight model can perform action selection across multiple diverse environments, a capability that would eliminate per-environment model maintenance