Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent terminology and style. Existing single-LLM methods are largely sentence-level, and multi-agent systems often use static workflows that do not adapt to scene complexity o...
Hai-Bo Jin, Xin-Jie Li, N. Sadoughi et al.· 0 citations
Agent harnesses govern how large language models (LLMs) gather context, invoke tools, verify results, preserve state, and terminate, largely affecting agent performance. However, the value of each harness mechanism can differ across heterogeneous tasks: a mechanism that improves one task may impose overhead or context...
Peng Kuang, Hai-Bo Jin, De-Hao Wu et al.· 0 citations
ANTMAN is introduced, an adaptive coordination framework that treats evolving unresolved information needs as the unit of runtime coordination and maintains a revisable Need Graph that tracks unresolved requirements, accumulated evidence, prior attempts, and search progress.
Jerry Wang, Hai-Bo Jin, Xiao-Peng Yuan et al.· 0 citations
This work introduces Tool Primitives, a design that replaces rigid API schema-based invocation with natural language as the interface for tool calling, where each tool is wrapped with an LLM interface that handles schema resolution and execution internally, enabling natural inter-tool communication for nested and multi...
Hai-Bo Jin, Sui-Jin Wang, Xuchen Yu et al.· 1 citation
This work presents a theoretical framework that reveals how reasoning steps can amplify error through three failure modes: incorrect sub-task decomposition, incorrect sub-task solving, and incorrect final answer summarization, and introduces structured interventions that adapt CoT generation according to the identified...
Haibo Jin, Peiyan Zhang, Man Luo et al.· Neural Information Processin...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.