3 papers
cs.AI2026
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
Minhua Lin, Juncheng Wu, Zijun Wang +14
LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing…
cs.IR2026
RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
Shijun Li, Wooseong Yang, Yu Wang +2
Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and natural-language reasoning abi…
cs.CL2025
GT2Vec: Large Language Models as Multi-Modal Encoders for Text and Graph-Structured Data
Jiacheng Lin, Kun Qian, Haoyu Han +9
Graph-structured information offers rich contextual information that can enhance language models by providing structured relationships and hierarchies, leading to more expressive e…