Papers

Filtered to self-distillation · clear filter

Browse by term

continual learning 91reinforcement learning 43vision-language models 18benchmarking 12benchmarks 11robotics 11large language models 10language models 9world models 9video generation 6generative models 5multimodal models 5natural language processing 5recursive self-improvement 5video world models 5agents 4dialogue systems 4diffusion models 4foundation models 4multimodal large language models 4on-policy distillation 4reasoning 4self-distillation 4self-supervised learning 4conversational AI 3evaluation benchmarks 3human-computer interaction 3LLMs 3multi-agent systems 3policy optimization 3

Matching papers

On-Policy Self-Distillation without Any Supervision

183 upvotes · 9 AUG 2026 · Yijiang Li, Bingyang Wang, Yijun Liang et al.

This paper shows how to make large language models improve themselves without needing external guidance or supervision, by using their own internal consistency to correct mistakes. Practitioners might care about this because it could lead to more robust and self-sufficient AI models.

self-distillationon-policy methodsunsupervised learninginternal consistencyreinforcement learningcontinual learning

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

179 upvotes · 30 SEP 2026 · Fang Wu, Da Xing, Yanjie Huang et al.

This paper introduces UniEvo-VL, a self-improvement framework for multimodal models that uses their own feedback to learn and improve, without relying on an external teacher. Practitioners might care because it can lead to better image generation capabilities and more efficient models.

multimodal modelsself-distillationcontinual learninggenerative modelsself-supervised learning

DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

88 upvotes · 19 AUG 2026 · Hangrui Xu, Jiarui Wang, Yang Yang et al.

This paper proposes a new framework for training autonomous agents to perform multi-turn tool-calling tasks, addressing the challenge of dealing with vast solution spaces by using a diamond topology-aware approach. Practitioners may care about this research because it can help improve the performance of autonomous agents in complex tasks.

self-distillationcontinual learninglarge language modelsinteraction-state transition graphsdiamond topology

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

84 upvotes · 8 JUL 2026 · Xinyu Geng, Xuanhua He, Sixiang Chen et al.

This paper introduces a framework called DeepSearch-Evolve, which helps train self-improving web agents by iteratively refining their performance using their own experience. Practitioners might care because this approach can lead to more efficient and effective agents that can learn from their own mistakes.

web agentsself-distillationcontinual learningreinforcement learningverifiable environments