This work’s contribution is not a new universal KG algorithm, but an empirical recipe for setting the structure boundary: compare against both low-and high-structure baselines, keep retrieval and reader stacks fixed when testing construction choices, report quality–cost frontiers, and require each added layer of graph structure to improve downstream utility.
Retrieval-augmented generation is becoming agentic. A search harness writes queries, reads results, reformulates, and decides when to stop. This largely solves accuracy: a harness with only BM25/grep and MiniMax M3 answers 85% of BrowseComp-Plus and 91% on multi-hop FRAMES in our runs, without compiled or vector indexe...
Zhi-Chang Yu, Bai-Ning Cao, Sbaaoui Idriss et al.· 0 citations
Many long-term memory systems for LLM agents are built around embedding-based retrieval. Al- though effective for semantic matching, similarity ranking alone does not establish whether re- trieved memories satisfy the conditions implied by a question. In this paper, we introduce KITE (Knowledge-Indexed Temporal Evidenc...
Feng Li, Kai-Lun Tan, Zhi-Bo Zhou et al.· 0 citations
Graph-based retrieval-augmented generation (GraphRAG) answers questions by retrieving over a knowledge graph built from a corpus. Yet retrieval strategies are designed around the structure their own construction pipeline produces, and whether they survive a change of construction is rarely tested. We study this cross-c...
Retrieval-augmented generation (RAG) grounds language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolated chunks without document structure, making it difficult to distinguish relevant evidence from chunks that merely resemble the query. Structure-aware methods such as Pa...
Meghanadh Pulivarthi, S. K. Biswal, Kushagra Bhushan et al.· 0 citations
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, cross-document reasoning at inference time, while precomputed structures like knowledge graphs often fall short because they rely on rigid he...
Anikait Singh, Teresa Zhang, Yoonho Lee et al.· 0 citations
Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right entities and properties and chains their relations. Language models offer a natural-language alternative but answer largely from memory, which is least reliable for less promi...
Mohamed Chenene, C. Rosas Hinostroza, Anastasia Stasenko et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.