Scholar
Jiangjie Chen
Google Scholar ID: XarNs8oAAAAJ
ByteDance Seed
Citations & Impact
Citations
2,246
H-index
21
i10-index
30
Publications
20
Co-authors
15
list available
Publications
Resume (English only)
Academic Achievements
- - Multiple papers selected as Spotlight papers at NeurIPS 2025, including ARIA, KORGym, ORIGAMISPACE, Enigmata; DAPO selected for poster presentation.
- - Papers Curse of Knowledge and LifeChoice accepted to EMNLP 2025 Findings.
- - Paper Past Meets Present won an Outstanding Paper Award at ACL 2025.
- - Proposed ARIA, a novel approach for training language agents with intention-driven reward aggregation, achieving 9.95% average performance gains across four downstream tasks.
- - Introduced MemAgent, a multi-conv RL-based memory agent that handles extremely long documents, extending from 8K context to 3.5M QA tasks with <5% performance loss and achieving 95%+ on 512K RULER test.
- - Released KORGym, a dynamic game platform offering over fifty games in textual or visual formats for interactive, multi-turn LLM reasoning evaluation with reinforcement learning scenarios.
- - Proposed Enigmata, a comprehensive suite of puzzles for improving logical reasoning of reasoning models, tailored for RLVR training.
- - Awarded Nomination Award for Outstanding Doctoral Dissertation of Shanghai Computer Society.
- - Papers DEEPER and HistoryAnalogy accepted to ACL 2025.
- - Paper CoSER accepted to ICML 2025.
- - Presented Seed-Thinking-v1.5, a cutting-edge reasoning model that’s incredible in math, code, science, and logical reasoning.
- - Proposed DAPO, a new critic-free RL algorithm that directly trains a pre-trained base model to SoTA performance on AIME 2024 without any SFT.
- - Four papers accepted to NAACL 2025: SelfGoal, EvoAgent, EasyTool, and Barrier in Language Agent Planning.
- - Three papers accepted to NeurIPS 2024 Workshop on Open-World Agents: EvoAgent, SelfGoal, and AucArena.
Research Experience
- - Researcher, ByteDance Seed, July 2024 – present
Education
- - Ph.D. in Computer Science, 2019 - 2024, Fudan University
- - B.S. in Computer Science (honors), 2014 - 2019, Fudan University
Background
- Jiangjie Chen is a researcher at ByteDance Seed Team. His current research interests are mostly around building reasoning models and autonomous agents:
- - Reasoning Models: Advancing research on incentivizing and understanding advanced reasoning and planning capabilities from large models.
- - 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.
Miscellany
- Interests: Large Language Models, Reasoning, Mountaineering, Tennis, Musicals
