DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents

arXiv:2610.02351 · cs.AI, cs.LG · Submitted 2026-10-01 · Read on arXiv

cs.AI, cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• AI Agents — 1× in this paper · explained in 2 episodes

Sources

• Enhancing LLM-Based Agents via Global Planning and Hierarchical Execution
• VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
• ReCreate: Reasoning and Creating Domain Agents Driven by Experience
• VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
• MemGPT: Towards LLMs as Operating Systems
• Qwen3 Technical Report
• AI scientists produce results without reasoning scientifically

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems