Qwen-3-8B-base

The 'Qwen-3-8B-Base' is a benchmark dataset used to evaluate the performance and reasoning capabilities of large language model agents in the context of self-evolution and tool integration.

Papers using Qwen-3-8B-base (5)

Clip Your Sequences Fairly: Enforcing Length Fairness for Sequence-Level RL2025 · 2 citesfg-expo: Frontier-guided exploration-prioritized policy optimization via adaptive kl and gaussian curriculum2026Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning2025OBLR-PO: A Theoretical Framework for Stable Reinforcement Learning2025Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning2025