7 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…
SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown
Yuxuan Liu, Haoran Li, Yuhao Zhang +10
Executable Agent Skills combine natural-language instructions and scripts into reusable packages for LLM agents, and revising them requires fixing errors without breaking correct b…
Can Language Models Imagine Without Seeing? Ekphrasis: Measuring Visual Creative Ideation in Text-Only LLMs
Hongyu Luo, He Wang, Huihao Jing +6
Current evaluations do not isolate whether text-only language models can originate visual concepts before image generation. Fluent visual prose can hide visual-plan failures: an an…
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…
MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning
Huihao Jing, Wenbin Hu, Hongyu Luo +4
Multi-agent systems (MAS), leveraging the remarkable capabilities of Large Language Models (LLMs), show great potential in addressing complex tasks. In this context, integrating MA…
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora
Jiaxin Bai, Wei Fan, Qi Hu +17
We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models t…