Skip to content
conftrace_
2026 EMNLP EMNLP 2026

RAMP: Adapting One Agent to Multiple Retrievers via Behavioral Probing

AbstractAgentic RAG agents must generate effective queries across diverse retriever backends, yet current agents produce retriever-oblivious queries, leading to large performance gaps when the backend changes. We observe that different retrievers, despite dissimilar architectures, exhibit structured behavioral patterns in their document-return overlap, forming a continuous behavioral space that can guide retriever-adaptive query generation. We propose RAMP (Retriever-Adaptive Multi-retriever Policy), which probes a black-box retriever with shared queries, encodes the resulting overlap patterns into a compact behavioral embedding, and injects it as soft tokens to condition query generation. A single RAMP model replaces four retriever-specific specialists without per-retriever retraining and generalizes to unseen retrievers by interpolating in behavioral space. On four QA benchmarks, RAMP matches 96–98% of four retriever-specific specialists (+3.8 EM over unconditioned training) and reaches 91.8% of the retrained upper bound on unseen retrievers, outperforming routing, few-shot, and fusion alternatives.

More from EMNLP 2026

All EMNLP 2026 papers →