30 July 2026 in Expert Systems with Applications
2 February 2026 in Neural Networks
11 November 2026 in IEEE Transactions on Knowledge and Data Engineering
31 March 2026 in SSRN Electronic Journal
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%).