Yiheng Zhuang
Research Subjects
Yiheng Zhuang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Wenlong Hou
School of Electronic and Information Engineering, Tongji University, Shanghai, China
4 shared publications - Xianhui Liu4 shared publications
- Yueying Liu4 shared publications
- Weidong Zhao
Tongji University
2 shared publications
Latest Publications
- 29 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
MOIE-KG: A multi-agent framework for ontology-guided open information extraction and knowledge graph construction
- 29 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
MOIE-KG: A multi-agent framework for ontology-guided open information extraction and knowledge graph construction
- 30 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
Planning as graphs: Adaptive agentic planning for LLM agents
- 30 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
Planning as graphs: Adaptive agentic planning for LLM agents
- Open Access
- 31 March 2026
- Published by Elsevier in SSRN Electronic Journal
Planning as Graphs: Adaptive Agentic Planning for LLM Agents
Planning is fundamental to LLM agents that solve complex, multi-step tasks, yet how to represent plans in a structured form that supports controllable execution remains an open challenge. Existing approaches often express plans as unstructured natural language or linear Chain-of-Thought (CoT), making it difficult to explicitly capture dependency structures among subtasks. They also lack outcome-conditioned transitions such as success/failure branches, limiting structured failure recovery during execution. We propose a Graph-based Adaptive Agentic Planner centered on a unified graph representation, GraphPlan, that jointly encodes prerequisite constraints and outcome-conditioned transitions, providing a structured substrate for failure localization and recovery. From a topological perspective, we show that CoT and unstructured planning are degenerate forms of GraphPlan under different constraints. Moreover, GraphPlan adaptively expands or collapses according to task complexity, enabling on-demand structuring. On SWE-bench Lite, a long-horizon interactive benchmark for repository-level repair, our method achieves a 51% resolution rate, substantially outperforming CoT (38%) and ReAct without planning (28.3%).
- 31 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessPlanning as Graphs: Adaptive Agentic Planning for LLM Agents
Planning is fundamental to LLM agents that solve complex, multi-step tasks, yet how to represent plans in a structured form that supports controllable execution remains an open challenge. Existing approaches often express plans as unstructured natural language or linear Chain-of-Thought (CoT), making it difficult to explicitly capture dependency structures among subtasks. They also lack outcome-conditioned transitions such as success/failure branches, limiting structured failure recovery during execution. We propose a Graph-based Adaptive Agentic Planner centered on a unified graph representation, GraphPlan, that jointly encodes prerequisite constraints and outcome-conditioned transitions, providing a structured substrate for failure localization and recovery. From a topological perspective, we show that CoT and unstructured planning are degenerate forms of GraphPlan under different constraints. Moreover, GraphPlan adaptively expands or collapses according to task complexity, enabling on-demand structuring. On SWE-bench Lite, a long-horizon interactive benchmark for repository-level repair, our method achieves a 51% resolution rate, substantially outperforming CoT (38%) and ReAct without planning (28.3%).
- 21 November 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 301
PARKA: Path-aware knowledge retrieval and structural-semantic knowledge adaptation for knowledge-based question answering
- 21 November 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 301
PARKA: Path-aware knowledge retrieval and structural-semantic knowledge adaptation for knowledge-based question answering