Reading - 分类 - vllbc02's blogs

Reading

2025

RAGEN：Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning 09-12

Parallel-R1：Towards Parallel Thinking via Reinforcement Learning 09-12

K2-Think：A Parameter-Efficient Reasoning System 09-12

Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following 09-12

EnvX：Agentize Everything with Agentic AI 09-12

AgentGym-RL：Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning 09-12

WebExplorer：Explore and Evolve for Training Long-Horizon Web Agents 09-10

The Majority is not always right：RL training for solution aggregation 09-10

TableMind：An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning 09-10

SFR-DeepResearch：Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents 09-10

1
2
3
4
5
14