19 papers
Evidence for Dynamical Filtering: High Binary Fraction, Hard-binary Excess, and Unresolved Triples in the Surviving Core of NGC 6791
Huanbin Chi, Zhi Li, Feng Wang +4
We present a deep photometric analysis of the main-sequence (MS) population in the old, metal-rich open cluster (OC) NGC 6791 using Gaia Data Release 3 data. After correcting for d…
Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Research Agents
Shuai Wang, Haodong Chen, Yu Yin +3
Existing deep-research agents use a Search--Visit workflow that retrieves whole webpages without considering the structure they expose through titles, headings, sections, and metad…
Reproducing LightMem: Naive RAG Is Just as Good for Memory Management
Yongjie Zhou, Shuai Wang, Bevan Koopman +1
Long-term conversational agents require access to information from earlier interactions, such as a user's preferences, past requests, or previously mentioned facts. Repeatedly prov…
Whole-Pool Setwise Reranking with Long-Context Language Models
Hang Li, Chuting Yu, Teerapong Leelanupab +2
Previous LLM-based passage re-rankers are often expensive and slow because the input context constraints require the LLM to make many dependent model calls. We study how recent lon…
On the impact of retrieved content representations in RAG Pipelines
Jonathan J Ross, Bevan Koopman, Anton van der Vegt +1
Retrieval-Augmented Generation (RAG) supplements a language model's input with retrieved documents, yet most RAG pipelines inherit retrieval components designed for human readers.…
Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings
Yu Yin, Shuai Wang, Bevan Koopman +1
Recent generative engine optimisation (GEO) research has shown that prompt-injection attacks can push a target product to the top of an LLM's recommendation list, with the stronges…