From Knowledge Access to Source Learning: Developing Source-Specific Competence
[Przetwarzanie języka] Autorzy: Lucheng Fu, Kejing Xia, Yiyang Wang i 10 więcej
Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods improve how source content is accessed and organized, while agent-memory systems preserve reusable knowledge from prior interactions, but repeated use of the same source is still largely treated as repeated access rather than an opportunity to progressively improve understanding of that source. We study source learning: developing reusable source-specific competence over a persistent authoritative source. We represent this competence with a persistent source model that captures reusable understanding of the source, including how its knowledge is structured, interpreted, and applied. To construct and progressively refine such models, we propose SourceLearn, which combines two complementary learning mechanisms. Self-Directed Source Learning i…
- Kategoria arxiv
- cs.CL
- Kategoria
- Przetwarzanie języka