4 papers
AdMem: Advanced Memory for Task-solving Agents
Runzhe Wang, Huilin Lu, Shengjie Liu +2
Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge. Prior memory ap…
Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages
Fan Wu, Lishuai Dong, Cuiyun Gao +4
Recent advancements in multimodal large language models (MLLMs) have achieved remarkable progress in multimodal reasoning and code generation, catalyzing a new paradigm for front-e…
Bridging Tool Dependencies and Domain Knowledge: A Graph-Based Framework for In-Context Planning
Shengjie Liu, Li Dong, Zhenyu Zhang
We present a framework for uncovering and exploiting dependencies among tools and documents to enhance exemplar artifact generation. Our method begins by constructing a tool knowle…
OrchDAG: Complex Tool Orchestration in Multi-Turn Interactions with Plan DAGs
Yifu Lu, Shengjie Liu, Li Dong
Agentic tool use has gained traction with the rise of agentic tool calling, yet most existing work overlooks the complexity of multi-turn tool interactions. We introduce OrchDAG, a…