GateReranker: Listwise Reranking with Joint Ranking and Adaptive Selection

Reranking is a crucial component in modern multi-stage retrieval and retrieval-augmented generation systems, where it is widely used to refine the ordering of candidate documents before downstream processing. In practical pipelines, however, the reranked list is usually followed by a selection step, such as fixed top-$K$ truncation or global score thresholding, to decide which documents should be retained. Such post-hoc selection strategies are simple and effective, but they rely on static decision rules and may be brittle across queries, domains, and candidate sets. In this work, we propose GateReranker, a listwise LLM reranker that unifies document ranking and adaptive selection within a single model. GateReranker introduces a dedicated gate token to learn a list-conditioned cutoff, allowing the model to retain documents whose relevance scores exceed the gate score while simultaneously producing their relative ordering. Experiments on BEIR show that GateReranker achieves the best retained-set F1 and the highest nDCG compared with strong open-source rerankers paired with fixed top-$K$ truncation and global score thresholding. These results suggest that adaptive selection can be naturally integrated into reranking, providing an effective in-model alternative to static post-hoc filtering.