Haoyue Zhao

Juntong Wang, Haoyue Zhao, guanghui Pan et al.

Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial cues, exploit reusable graph-structrual roles, and improve the memory itself through downstream feedback. We introduce SAGE, a Self-evolving Agentic Graph-memory Engine that models graph memory as a dynamic long-term memory substrate. SAGE couples two roles: a memory writer that incrementally constucts structured graph memory from interaction histories, and a Graph Foundation Model-based memory reader to perform retrieval and provide feedback to the memory writer. We provide rigorooous theoretical annalyses supporting the framework. Across multi-hop QA, open-domain retireval, domain-specific review QA, and long-term agent-memory benchmarks, SAGE improves evidence recovery, answer grounding, and retrieval efficiency: after two self-evolution rounds, it achieves the best average rank on multi-hop QA; in zero-shot open-domain transfer, it reaches 82.5/91.6 Recall@2/5 on NQ. Further results on LongMemEval and HaluMem show that traning and reader-writer feedback improve multiple long-term memory and hallucination-diagnostic metrics, suggesting that self-evolving, structure-aware graph memory is a promising foundation for robust long-horizon language agents.

Haoyue Zhao, Xin Guan, Qiang Li

The existing piano fingering labeling statistical models usually consider the constraints among the fingers and the correlation between fingering and notes, and rarely include the relationship among the notes directly. The limited learned finger-transfer rules often cause that some parts of the fingering cannot be playable in fact. And traditional models often adopt the original notes, which cannot help to explore the mapping nature between the pitches and fingering. Inspired from manual-ly annotation which acquire the fingering knowledge directly from pitch-difference, we proposed a pitch-difference sequence and fingering (PdF) matching model. And to get playable fingering, be-sides learned finger-transfer rules, prior finger-transfer knowledge is especially combined into the model. In order to characterize the playable performance of the model, we also presented a new evaluation index named incapable-performing fingering rate (IFR). Comprehensive experimental re-sults show that compared with the existing state-of-the-art third-order hidden Markov labeling model, the general and the highest matching rate of our model increases by 3% and 1.6% respective-ly, and the fingering for all scores can be playable.