【论文合集】大模型代理论文 agent paper list

《Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimization》​

论文链接:[2504.17355] Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimization

《Towards a HIPAA Compliant Agentic AI System in Healthcare》​

论文链接:[[2504.17355] Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimization](https://arxiv.org/abs/2504.17355)

代码链接:https://github.com/zoharri/mamba

《ADAPTER-RL: Adaptation of Any Agent using Reinforcement Learning》​

论文链接:ADAPTER-RL: Adaptation of Any Agent using Reinforcement Learning | OpenReview

代码链接:https://github.com/sgoodfriend/rl-algo-impls/blob/main/rl_algo_impls/microrts/technical-description.md?utm_source=catalyzex.com

《Online Continual Learning for Interactive Instruction Following Agents》​

论文链接:Online Continual Learning for Interactive Instruction Following Agents | OpenReview

代码链接:https://github.com/snumprlab/cl-alfred

《STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models》​

论文链接:STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models | OpenReview

代码链接:https://github.com/ibm/starling-agent

《MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning》​

论文链接:[2505.20670] MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning

《Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System》​

论文链接:[2505.20310] Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System

代码链接:GitHub - black-yt/Manalyzer: Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

精通代码大仙

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值