ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation
cs.LG, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/THUDM/slime2https:
Terminology
Sources
- Qwen3-VL Technical Report
- Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
- Sample-Efficient Learning from Agent Experience
- Reinforcement Learning via Self-Distillation
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- Privileged Information Distillation for Language Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Distillation Enables Continual Learning
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
- Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
- Qwen3 Technical Report
- Online Experiential Learning for Language Models
- Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks