Chain-of-Experience for Continual LLM Improvement
Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inference-time interaction. In this paper, we study how LLMs learn from iterative experience at test time, a setting we refer to as Chain-of-Experience (CoE), where models accumulate experiential traces through iterative interactions with self or environmental feedback to form a continual improvement loop beyond zero-shot inference. We instantiate CoE with diverse feedback mechanisms, including model self-feedback and environmental signals such as
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%Exploring continual learning without replay buffers: Our findings using dynamic task-similarity routing [P] →
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Haoqin Tu →
“Chain-of-Experience for Continual LLM Improvement”
- LinkedLinked via arxiv author · 85%Yunhao Fang →
“Chain-of-Experience for Continual LLM Improvement”
- LinkedLinked via arxiv author · 85%Yizhong Wang →
“Chain-of-Experience for Continual LLM Improvement”
- LinkedLinked via arxiv author · 85%Cihang Xie →
“Chain-of-Experience for Continual LLM Improvement”
- LinkedLinked via arxiv author · 85%Shen Yan →
“Chain-of-Experience for Continual LLM Improvement”