SGG-ReflAct: Sub-Goal Guided ReflAct with Structured Planning for Reliable Long-Horizon Reasoning
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models
- Language Models are Few-Shot Learners
- ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
- TextWorld: A Learning Environment for Text-based Games
- PlanU: Large Language Model Reasoning through Planning under Uncertainty
- The Llama 3 Herd of Models
- Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
- Reasoning with Language Model is Planning with World Model
- Interactive Fiction Games: A Colossal Adventure
- TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents
- RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents
- ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
- Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
- AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
- Self-Refine: Iterative Refinement with Self-Feedback
- Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
- Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents
- Reflexion: Language Agents with Verbal Reinforcement Learning
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