self-reflection
Self-reflection in the context of AI refers to the capability of a model or agent to evaluate its own decision-making processes, learn from past actions, and potentially improve its future performance.
- Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
- GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
- Learning to Reason under Off-Policy Guidance
- R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
- Reinforcement Learning for Reasoning in Large Language Models with One Training Example
- SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
- Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
- VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
- When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs