Think with Skills: Pseudocode Planning Before Execution for Advanced Reasoners
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
- SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
- Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Beyond Instruction Following: Learning Grounded Skill-Following with Skill Contracts
- Skill Retrieval Augmentation for Agentic AI
- Reinforcement Learning for Self-Improving Agent with Skill Library
- Generative Skill Composition for LLM Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents