LLMpeople
Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Chao Xin

Public evidence identifies Chao Xin as a ByteDance Seed paper author, including the Seed1.5-Thinking report and the OpenReview paper PAG on LLM self-correction with multi-turn reinforcement learning.

Co-author on ByteDance Seed large-language-model reasoning and reinforcement-learning research.1 organizations1 reports

Profile status: updated

updated 2 public sources
large language modelsreinforcement learningreasoningself-correction

Current frame

Co-author on ByteDance Seed large-language-model reasoning and reinforcement-learning research.

Extended note

Chao Xin is publicly listed as an author on ByteDance Seed's 2025 report "Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning" and on the 2025 OpenReview paper "PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier." These sources support a conservative profile centered on large language models, reasoning, self-correction, and reinforcement learning. No reliable public homepage, team biography, education history, or standalone profile details were found within the exact-source search budget, so biographical claims are intentionally minimal.

Organizations

core ByteDance Seed

Reports

Report Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Official and primary sources

PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier Official source · openreview · OpenReview

Supporting sources

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning Supporting source · report · arXiv