5 papers
DPA-MoE: A Runtime Precision Control Framework for MoE Inference
Jaeyun Kim, Hoonki Lee, Susie Shin +3
Mixture-of-Experts (MoE) models reduce computation by routing each token to a small set of experts, but each selected expert is still used at a fixed precision. We present DPA-MoE,…
When Is Enough Not Enough? Illusory Completion in Search Agents
Dayoon Ko, Jihyuk Kim, Sohyeon Kim +5
In agentic search, an LLM agent searches the web, reads the pages it finds, and decides what to look for next before returning an answer. But can we trust an answer simply because…
Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning
Dayoon Ko, Jihyuk Kim, Haeju Park +6
Large reasoning models (LRMs) combined with retrieval-augmented generation (RAG) have enabled deep research agents capable of multi-step reasoning with external knowledge retrieval…
Shifting from Ranking to Set Selection for Retrieval Augmented Generation
Dahyun Lee, Yongrae Jo, Haeju Park +1
Retrieval in Retrieval-Augmented Generation(RAG) must ensure that retrieved passages are not only individually relevant but also collectively form a comprehensive set. Existing app…
Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering
Yongho Song, Dahyun Lee, Myungha Jang +4
The long-standing goal of dense retrievers in abtractive open-domain question answering (ODQA) tasks is to learn to capture evidence passages among relevant passages for any given…