Jiangjie Chen

Jiangjie Chen

Researcher

ByteDance Seed

Biography

Jiangjie Chen (陈江捷) is a researcher at ByteDance Seed Team. In 2024, he earned his Ph.D. at Fudan University in the School of Computer Science, Shanghai, China. His current interested research topics are mostly around building reasoning models and autonomous agents:

  1. Reasoning Models: Advancing research on incentivizing and understanding advanced reasoning and planning capabilities from large models.
  2. Autonomous Agents: Developing advanced methods for autonomous, trustworthy, and personalized agents. This extends towards the exploration of their interactions with multiple agents and real environments.
Interests
  • Large Language Models
  • Reasoning
  • Mountaineering 🧗‍♂️
  • Tennis 🎾
  • Musicals
Education

  • Ph.D. in CS, 2019 - 2024

    Fudan University

  • B.S. in CS (honors), 2014 - 2019

    Fudan University

News

  • Jul. 2025: Our paper Past Meets Present won an Outstanding Paper Award at ACL 2025!

  • Jul. 2025: Check out our work on spatial cognition! Can LLMs Learn to Map the World from Local Descriptions? We demonstrate that LLMs can develop spatial awareness from fragmented local observations, successfully learning spatial perception and navigation in urban environments!

  • Jul. 2025: Check out ARIA! We propose a novel approach for training language agents with intention-driven reward aggregation. By projecting natural language actions into a lower-dimensional intention space, ARIA reduces reward variance and improves policy optimization, achieving 9.95% average performance gains across four downstream tasks.

  • Jul. 2025: Check out MemAgent! We introduce a novel approach to handling extremely long documents in language models through a multi-conv RL-based memory agent. MemAgent extends from 8K context to 3.5M QA tasks with <5% performance loss and achieves 95%+ on 512K RULER test!

  • May. 2025: Check out KORGym! We introduce a dynamic game platform offering over fifty games in textual or visual formats for interactive, multi-turn LLM reasoning evaluation with reinforcement learning scenarios. Our platform reveals consistent reasoning patterns within model families and demonstrates superior performance of closed-source models.

  • May. 2025: Check out Enigmata! We propose a comprehensive suite of puzzles for improving logical reasoning of reasoning models, tailored for RLVR training. We find that not only do such puzzles drastically improve puzzle reasoning of LLMs, but also improve SoTA models such as Seed1.5-Thinking on challenging reasoning tasks such as AIME and GPQA! This is a free lunch for SoTA models, since Enigmata is synthetic and can be generated at scale!

  • May. 2025: I was awarded with Nomination Award for Outstanding Doctoral Dissertation of Shanghai Computer Society!

  • May. 2025: Our papers DEEPER and HistoryAnalogy are accepted to ACL 2025!

  • May. 2025: Our paper CoSER is accepted to ICML 2025! Check out this comprehensive resource for role-playing agents!

  • Apr. 2025: Presenting Seed-Thinking-v1.5 from ByteDance Seed Team, a cutting-edge reasoning model that’s incredible in math, code, science, and logical reasoning!

  • Mar. 2025: DAPO is out! A new critic-free RL algorithm that directly trains a pre-trained base model to SoTA performance on AIME 2024 without any SFT.

  • Mar. 2025: Four papers accepted to NAACL 2025: SelfGoal, EvoAgent, EasyTool and Barrier in Language Agent Planning.

  • Oct. 2024: Three papers accepted to NeurIPS 2024 Workshop on Open-World Agents: EvoAgent, SelfGoal and AucArena. See you in Vancouver!

  • Sep. 2024: Our survey paper on role-playing agents is accepted to TMLR!

  • Sep. 2024: We have three accepted papers in EMNLP 2024! Two main papers are Segment+ on long-context processing with short-context models, and CROSS on role-playing evaluation, and one finding paper DetectBench on benchmarking detective reasoning.

  • Jul. 2024: Our work on Irrelevant Evidence got accepted in COLM 2024!

  • Jul. 2024: I have graduated from Fudan University, and will officially join ByteDance Seed Team as a Full-time researcher.

Experience

 
 
 
 
 
ByteDance Seed
Researcher
ByteDance Seed
Jul 2024 – Present Shanghai, China
 
 
 
 
 
Allen Institute for AI
Research Intern
Allen Institute for AI
Jun 2023 – Sep 2023 Seattle, Washington, U.S.
Aristo Team, mentored by Dr. Kyle Richardson. Responsibilities: Work on multi-agent reasoning and planning with large language models.
 
 
 
 
 
UC Santa Barbara
Visiting Research Intern
UC Santa Barbara
Sep 2021 – May 2023 Remote
Hosted by Prof. Lei Li. Responsibilities: Work on machine reasoning over language with large language models.
 
 
 
 
 
ByteDance AI Lab
Research Intern
ByteDance AI Lab
Nov 2019 – May 2023 Shanghai, China
Mentored by Prof. Lei Li, Prof. Hao Zhou, and Dr. Changzhi Sun. Work on Knowledge-guided text generation and natural language reasoning.

Awards

ACL 2025 Outstanding Paper Award
Association for Computational Linguistics Jul 2025
Nomination Award for Outstanding Doctoral Dissertation of Shanghai Computer Society
Shanghai Computer Society May 2025
Excellent Graduates of Shanghai
Fudan University Apr 2024
ACL 2023 Outstanding Paper Award
Association for Computational Linguistics Jul 2023
China National Scholarship for Doctoral Students
Fudan University Oct 2022
Honor Student Award in Computer Science of Top Talent Undergraduate Training Program
Fudan University Jun 2019

Featured Publications

Hongli Yu, Tinghong Chen, Jiangtao Feng, Jiangjie Chen, Weinan Dai, Qiying Yu, Ya-Qin Zhang, Wei-Ying Ma, Jingjing Liu, Mingxuan Wang, Hao Zhou
July, 2025 Preprint
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

MemAgent introduces a multi-conv RL-based memory agent that enables language models to handle extremely long documents, extending from 8K to 3.5M tokens with minimal performance degradation.
PDF Cite Project Project
Jiangjie Chen, Qianyu He, Siyu Yuan, Aili Chen, Zhicheng Cai, Weinan Dai, Hongli Yu, Qiying Yu, Xuefeng Li, Jiaze Chen, Hao Zhou, Mingxuan Wang
May, 2025 Technical Report
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

We introduce Enigmata, the first comprehensive suite tailored for improving LLMs with puzzle reasoning skills.
PDF Cite Dataset Project Code Model
ByteDance Seed
April, 2025 Technical Report
Seed-Thinking-v1.5: Advancing Superb Reasoning Models with Reinforcement Learning
Seed-Thinking-v1.5: Advancing Superb Reasoning Models with Reinforcement Learning

We introduce Seed-Thinking-v1.5, a Mixture-of-Experts (MoE) model with a relatively small size, featuring 20B activated and 200B total parameters, capable of reasoning through thinking before responding, resulting in improved performance on a widerange of benchmarks.
PDF Project
Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Tiantian Fan, Gaohong Liu, Lingjun Liu, Xin Liu, Haibin Lin, Zhiqi Lin, Bole Ma, Guangming Sheng, Yuxuan Tong, Chi Zhang, Mofan Zhang, Wang Zhang, Hang Zhu, Jinhua Zhu, Jiaze Chen, Jiangjie Chen, Chengyi Wang, Hongli Yu, Weinan Dai, Yuxuan Song, Xiangpeng Wei, Hao Zhou, Jingjing Liu, Wei-Ying Ma, Ya-Qin Zhang, Lin Yan, Mu Qiao, Yonghui Wu, Mingxuan Wang
March, 2025 Preprint
DAPO: An Open-source LLM Reinforcement Learning System At Scale
DAPO: An Open-source LLM Reinforcement Learning System At Scale

We introduce DAPO, a Decoupled Clip and Dynamic sAmpling Policy Optimization algorithm, and fully open-source a state-of-the-art large-scale RL system that achieves 50 points on AIME 2024 using Qwen2.5-32B base model.
PDF Cite Dataset Project Code Model
Aili Chen, Xuyang Ge, Ziquan Fu, Yanghua Xiao, Jiangjie Chen
September, 2024 Preprint
TravelAgent: An AI Assistant for Personalized Travel Planning
TravelAgent: An AI Assistant for Personalized Travel Planning

We introduce TravelAgent, an LLM-powered travel planning system that generates rational, comprehensive, and personalized itineraries through four modules, demonstrating effectiveness in dynamic scenarios.
PDF Cite Demo
Jian Xie, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, Yuandong Tian, Yanghua Xiao, Yu Su
February, 2024 In The Forty-first International Conference on Machine Learning (ICML 2024), Spotlight
TravelPlanner: A Benchmark for Real-World Planning with Language Agents
TravelPlanner: A Benchmark for Real-World Planning with Language Agents

We introduced TravelPlanner, a benchmark for assessing language agents’ planning abilities, showing that even advanced models like GPT-4 face difficulties with complex tasks.
PDF Cite Dataset Code Demo
Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou, Yu Su
May, 2023 In The Twelfth International Conference on Learning Representations (ICLR 2024), Spotlight
Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts

We present the first comprehensive and controlled investigation into the behavior of large language models when encountering knowledge conflicts.
PDF Cite Code
Siyu Yuan, Jiangjie Chen, Ziquan Fu, Xuyang Ge, Soham Shah, Charles Robert Jankowski, Yanghua Xiao, Deqing Yang
May, 2023 In The 61th Annual Meeting of the Association for Computational Linguistics (ACL 2023), Outstanding Paper Award
Distilling Script Knowledge from Large Language Models for Constrained Language Planning
Distilling Script Knowledge from Large Language Models for Constrained Language Planning

We propose an over-generate-then-filter approach to improve large language models (LLMs) on constrained language planning, and use it to distill a novel constrained language planning dataset, CoScript.
PDF Cite Poster Slides Code

Recent Publications

Quickly discover relevant content by filtering publications.
Hongli Yu, Tinghong Chen, Jiangtao Feng, Jiangjie Chen, Weinan Dai, Qiying Yu, Ya-Qin Zhang, Wei-Ying Ma, Jingjing Liu, Mingxuan Wang, Hao Zhou (2025). MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent. Preprint.

PDF Cite Project Project

Ruihan Yang, Yikai Zhang, Aili Chen, Xintao Wang, Siyu Yuan, Jiangjie Chen, Deqing Yang, Yanghua Xiao (2025). ARIA: Training Language Agents with Intention-Driven Reward Aggregation. Preprint.

PDF Cite

Sirui Xia, Aili Chen, Xintao Wang, Tinghui Zhu, Yikai Zhang, Jiangjie Chen, Yanghua Xiao (2025). Can LLMs Learn to Map the World from Local Descriptions?. Preprint.

PDF Cite

Jiangjie Chen, Qianyu He, Siyu Yuan, Aili Chen, Zhicheng Cai, Weinan Dai, Hongli Yu, Qiying Yu, Xuefeng Li, Jiaze Chen, Hao Zhou, Mingxuan Wang (2025). Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles. Technical Report.

PDF Cite Dataset Project Code Model

Jiajun Shi, Jian Yang, Jiaheng Liu, Xingyuan Bu, Jiangjie Chen, Junting Zhou, Kaijing Ma, Zhoufutu Wen, Bingli Wang, Yancheng He, Liang Song, Hualei Zhu, Shilong Li, Xingjian Wang, Wei Zhang, Ruibin Yuan, Yifan Yao, Wenjun Yang, Yunli Wang, Siyuan Fang, Siyu Yuan, Qianyu He, Xiangru Tang, Yingshui Tan, Wangchunshu Zhou, Zhaoxiang Zhang, Zhoujun Li, Wenhao Huang, Ge Zhang (2025). KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation. Technical Report.

PDF Cite Project

See all publications

Popular Topics

Agent Analogical Reasoning Benchmark Constrained Generation Dataset Diversified Generation Explainable NLP Faithfulness and Factuality Information Extraction Knowledge Graph Large Language Models Large Reasoning Models LLM Analysis Planning Reasoning Reinforcement Learning Retrieval Role-Playing Agent Simulated Environment Text Generation

Visitors