Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning
"结构化推理" 相关文章
Fortifying LLM-Based Code Generation with Graph-Based Reasoning on Secure Coding Practices
AI“以小博大”新标杆：三星开源 TRM 模型，700 万参数、特定任务性能媲美 Deepseek R1 等万倍大模型
AI“以小博大”新标杆：三星开源 TRM 模型，700 万参数、特定任务性能媲美 Deepseek R1 等万倍大模型
StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering
STRIVE: Structured Reasoning for Self-Improvement in Claim Verification
Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates
TreeGPT: Pure TreeFFN Encoder-Decoder Architecture for Structured Reasoning Without Attention Mechanisms
AgentCDM: Enhancing Multi-Agent Collaborative Decision-Making via ACH-Inspired Structured Reasoning
解密prompt系列58. MCP - 工具演变 & MCP基础
I2I-STRADA -- Information to Insights via Structured Reasoning Agent for Data Analysis
大模型不再“自由发挥”？KAG-Thinker引入结构化思维，重塑大模型复杂推理范式
大模型不再“自由发挥”？KAG-Thinker引入结构化思维，重塑大模型复杂推理范式
KAG-Thinker：「结构化」思考新范式，支持逻辑严谨的大模型复杂推理
让AI也会“权衡利弊”？DecisionFlow让大模型更懂高风险决策！
Beyond Aha Moments: Structuring Reasoning in Large Language Models
This AI Paper Introduces RL-Enhanced QWEN 2.5-32B: A Reinforcement Learning Framework for Structured LLM Reasoning and Tool Manipulation
Outcome-Refining Process Supervision: Advancing Code Generation with Structured Reasoning and Execution Feedback
o1的风又吹到多模态，直接吹翻了GPT-4o-mini
智能体首次达到Kaggle Grandmaster水平，华为用结构化推理补齐思维链短板
