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

Chetan Bansal

ACL 2026×2ICLR 2026VLDB 2026智能体与工具强化学习与后训练理论与学习动力学数据与预训练对齐与偏好
新星分贡献者
61
一作贡献0
核心/参与24
方向广度16
合作网络12
0 一作 · 4 篇 · ACL 2026 / ICLR 2026 / VLDB 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 #8/12ACL 2026Poster· Natural Language Processing

S ynth A gent: Adapting Web Agents with Synthetic Supervision

Zhaoyang Wang · Yiming Liang · Xuchao Zhang · Qianhui Wu · Siwei Han · Anson Bastos · Rujia Wang · Chetan Bansal · Baolin Peng · Jianfeng Gao · Saravan Rajmohan · Huaxiu Yao

摘要

Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues where synthesized tasks contain hallucinations that cann...

数据与预训练智能体与工具对齐与偏好OpenReview 项目页
作者位次 #6/7ACL 2026Findings· Findings of ACL

Learning Optimal Message Representations for Agentic Communication

Shashwat Gupta · Anson Bastos · Mayukh Das · Supriyo Ghosh · Nagarajan Natarajan · Chetan Bansal · Saravan Rajmohan

摘要

Large Language Models (LLMs) have demonstrated remarkable capabilities in agentic collaborative problem-solving, albeit a gap exists. Existing frameworks predominantly rely on natural language as a primary representation (format) for agentic communication. However natural language could be ambigu...

评测与基准智能体与工具可解释性OpenReview 项目页

常见合作者