9 papers
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
Zhengye Bao, Shengtao Zhang, Haokai Zhang +3
LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other comple…
TRACE: Governing Memory Validity in Evolving Multi-Agent Systems
Wenjun Xiong, Shengtao Zhang, Shangding Gu +5
Persistent memory lets language-model agents carry information across long-running collaborations, but leaves a lifecycle question open: what may a returning agent still act on onc…
Spatial Memory Agent: Experience-Grounded Procedural Memory for Spatial Intelligence
Haokai Zhang, Yuhang Ding, Yunshu Zhou +5
Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To improve the spatial reasoning ability of VLMs, existing work has…
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
Junwei Liao, Haoting Shi, Ruiwen Zhou +9
Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation withou…
Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
Yujie Zheng, Zhuo Li, Shengtao Zhang +8
Deploying Large Language Models to data-scarce programming domains poses significant challenges, particularly for kernel synthesis on emerging Domain-Specific Architectures where a…
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou +11
The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evo…
A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories
Haojun Yu, Youcheng Li, Zihan Niu +19
Breast ultrasound (BUS) is an essential tool for diagnosing breast lesions, with millions of examinations per year. However, publicly available high-quality BUS benchmarks for AI d…
PTCL: Pseudo-Label Temporal Curriculum Learning for Label-Limited Dynamic Graph
Shengtao Zhang, Haokai Zhang, Shiqi Lou +4
Dynamic node classification is critical for modeling evolving systems like financial transactions and academic collaborations. In such systems, dynamically capturing node informati…
Unveiling the Hidden: Movie Genre and User Bias in Spoiler Detection
Haokai Zhang, Shengtao Zhang, Zijian Cai +4
Spoilers in movie reviews are important on platforms like IMDb and Rotten Tomatoes, offering benefits and drawbacks. They can guide some viewers' choices but also affect those who…