Artificial Intelligence · 24.08.2026, 07:01 UTC
Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflows
| Schweregrad | info |
|---|---|
| Kategorie | Artificial Intelligence |
| Quelle | arXiv cs.AI ↗ |
| Veröffentlicht | 24.08.2026 UTC |
Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.
arXiv:2604.22820v2 Announce Type: replace-cross Abstract: Long-horizon tool-using tasks sometimes benefit from revisiting earlier subtasks, but explicit revisitation also adds routing, coordination, and token cost. We study complete cyclic subtask graphs for large language model (LLM) agents: a workflow controller in which executable subtasks are fully connected and a unified state-analysis-and-routing agent selects transitions from natural-language criteria. We evaluate task-specific (Spec-Cyc) and benchmark-generic (Gen-Cyc) cyclic graphs on TextCraft, ALFWorld, and Finance-Agent against ReAct and dependency-directed workflows. Our main dependency-directed controller is DepDAG, which permits same-subtask retry while preserving forward dependency constraints. The evaluated case studies suggest three workflow signatures rather than a universal architecture ranking. TextCraft behaves like a prerequisite-chain setting, where cyclic routing often adds overhead. ALFWorld behaves like a partially observable recovery setting, where explicit revisitation improves exploration and success. Finance-Agent behaves like an open-ended evidence-synthesis setting, where workflow control alone is insufficient without stronger retrieval, grounding, and verification mechanisms. We add a qualified workflow-signature matrix, fault-injection robustness analysis, token-cost accounting, graph-stability reporting, transition-audit checks for DepDAG, and failure-mode structure for trajectory analysis. Overall, complete cyclic subtask graphs are best understood as a diagnostic workflow-control …
Maßnahmen
⬇ Als MarkdownVerwandte Beiträge
- info BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning
- info Causal Modeling of Adverse Pregnancy Outcomes via Adaptive LLM Proposals
- info Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment
- info RODE: A Radial-Orthogonal Decoupled Engine for Optimization