15 papers
MOSAIC: An Omni-Modal Benchmark for Long-Term Memory and Cross-Modal Reasoning in Conversational Agents
Hong Ting Tsang, Boyi Zhang, Haoyu Huang +7
Omni-modal assistants must remember not only what users say, but also what they show and convey. Existing long-term memory benchmarks are mostly text-and-image or report a single e…
RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving
Huihao Jing, Wenbin Hu, Shaojin Chen +6
Prefix reuse improves LLM inference by sharing the KV cache of common prompt prefixes. This helps only if the scheduler can execute a matched branch in the current worker round. Sc…
Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization
Huihao Jing, Shaojin Chen, Wenbin Hu +5
As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central safety problem. Guardrails are…
SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition
Yuxuan Liu, Zhaochen Su, Hangyu Guo +11
Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evaluation is to expand task requir…
SoFT: Soft Targets for Generalizable LLM Fine-Tuning
Huihao Jing, Wenbin Hu, Shaojin Chen +7
Distillation enables student language models to acquire new capabilities from expert teachers. However, integrating knowledge from multi-teacher, multi-domain demonstrations into a…
Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds
Yuxuan Liu, Zhaochen Su, Yuhao Zhang +9
Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying model. Yet it remains unclear when…
Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions
Huihao Jing, Wenbin Hu, Shaojin Chen +10
The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only…
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
Yuxuan Liu, Zhaochen Su, Lingyun Xie +11
Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures. Existing self-evolving methods refine skills using…
KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning
Yisen Gao, Jiaxin Bai, Haoyu Huang +5
Knowledge graph (KG) foundation models aim to generalize to graphs with unseen entities and relations by learning transferable relational structure. Most existing methods, however,…
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
Xiyu Ren, Zhaowei Wang, Yiming Du +11
Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capability: long-context LVLMs and m…
PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments
Jiaxin Bai, Yue Guo, Yifei Dong +13
World models for interactive text agents must typically be learned from observation-action trajectories alone. Specifically, the environment returns text observations after each ac…
DeepRefine: Agentic Knowledge Refinement via Reinforcement Learning
Haoyu Huang, Jiaxin Bai, Shujie Liu +7
External knowledge enables large language model (LLM) agents to ground their actions and decisions beyond intrinsic parametric memory in open-ended, knowledge-intensive downstream…
NGDBench: Towards Neural Graph Data Management
Yufei Li, Yisen Gao, Jiaxuan Xiong +6
Data critical to real-world decision-making is increasingly found within organizations. Such data is heterogeneous, constantly evolving, and only imperfectly captured. However, cur…
NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training
Zhongwei Xie, Jiaxin Bai, Shujie Liu +5
Neural Graph Databases (NGDBs) facilitate complex logical reasoning over incomplete knowledge structures, yet their training efficiency and expressivity are constrained by rigid qu…
Top Ten Challenges Towards Agentic Neural Graph Databases
Jiaxin Bai, Zihao Wang, Yukun Zhou +16
Graph databases (GDBs) like Neo4j and TigerGraph excel at handling interconnected data but lack advanced inference capabilities. Neural Graph Databases (NGDBs) address this by inte…