paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
SC

Shihao Cai

ACL 2026×2ICLR 2026KDD 2026智能体与工具评测与基准数据与预训练强化学习与后训练长上下文与架构
新星分新星
81
一作贡献40
核心/参与22
方向广度16
合作网络12
1 一作 · 4 篇 · ACL 2026 / ICLR 2026 / KDD 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

4
作者位次 #2/18ACL 2026Findings· Findings of ACL

Towards General Agentic Intelligence via Environment Scaling

Runnan Fang · Shihao Cai · Baixuan Li · Jialong Wu · Guangyu Li · Wenbiao Yin · Xinyu Wang · Xiaobin Wang · Liangcai Su · Zhen Zhang · Shibin Wu · Zhengwei Tao · Yong Jiang · Pengjun Xie · Ningyu Zhang · Fei Huang · Wentao Zhang · Jingren Zhou

摘要

Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. The...

智能体与工具强化学习与后训练评测与基准OpenReview 项目页
作者位次 #5/8ACL 2026Findings· Findings of ACL

U -Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents

Jin Su · Runnan Fang · Yeqiu Li · Xiaobin Wang · Shihao Cai · Pengjun Xie · Ningyu Zhang · Fajie Yuan

摘要

Large language model (LLM)-based agents have been successfully deployed in many tool-augmented settings, but their scalability is fundamentally constrained by context length. Existing context-folding methods mitigate this issue by summarizing past interactions, yet they are typically designed for...

智能体与工具长上下文与架构评测与基准OpenReview 项目页

常见合作者