Repository Issue Activity (beta)

#93 VOKO —— 面向 AI 智能体的跨平台 IM 与协作运行时

#89 w

#87 the difference between this one and another repo？

#27 [FEAT]: 可以建一个微信群不

#85 [FEAT]: Best practices for integrating external memory (e.g. mem0) into the Agent for GRPO training

#83 [ORG]: clean the code

#75 [FEAT]: adding some explainability and control for operations for code through metaprogramming

#15 The wechat group is full and need to be invited to join

#73 [BUG]: 没有函数

#74 [BUG]: final_env_score永远等于0

#40 全球顶尖的AI编码助手，采用Claude 3.7等大模型自主训练

#57 [BUG]: Run MCP Failed

#44 [BUG]: 请问这么多的环境依赖以哪一个为主呢，我想跑通train_ppo.sh

#17 Recommand our work AgentRefine as the training set

#42 [EXP]: Is the RL agent training code still under development?

#2 Question about how to get the trajectory label

#31 [FEAT]:

#26 Typo in repo "Description" setting

#24 Question about Multi-Modal Training

#21 [BUG]: ValueError: The global train batch size (1 x 1) must be evenly divisible by the number of generations per prompt (8). Given the current train batch size, the valid values for the number of generations are: [].

#8 TypeError: Couldn't cast array of type

#10 Train error

#7 I can't find CharlieDreemur/OpenManus-RL-GRPO dataset.

#5 installation error

#4 开源社区无法进入