task decomposition
Task decomposition involves breaking down complex tasks into smaller, manageable sub-tasks, allowing models to learn and optimize each component more effectively and improve overall efficiency in problem-solving.
- AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
- Cognitive Predictive Processing: A Human-inspired Framework for Adaptive Exploration in Open-World Reinforcement Learning
- InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning
- Lost in Transmission: When and Why LLMs Fail to Reason Globally
- Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
- OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
- OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling
- RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks