• I am an Applied Scientist II at Amazon since May 2024. Before joining Amazon, I obtained CS PhD from Georgia Institute of Technology specializing in Machine Learning and was co-advised by Prof. Srijan Kumar and Prof. Mustaque Ahamad.
• My research interests include Large Language Model, Natural Language Processing (NLP), Deep Learning, and Reinforcement Learning. Especially at Amazon, I work on large language models (LLM) post-training (e.g., alignment, reasoning, evaluation, SFT, and RL) and self-improving coding&ads agents.
• I am always available for academic collaborations from academia and industry. Please feel free to contact me if you have research ideas or industry collaborations. I am more than happy to discuss and collaborate with you.
• Contact: bhe46[at]gatech.edu / bing.he[at]cc.gatech.edu / LinkedIn Message

News

• [2026.08]

  Two papers on self-evolving LLM agents — Harness Updating Is Not Harness Benefit and Evo-Harness — accepted to the EMNLP 2026 main conference! Thanks to our interns and collaborators!

• [2026.07]

  Updated our benchmark blog with Kimi-K3 results — a three-family open-source comparison across Qwen3.5, GLM5.2, and Kimi-K3.

• [2026.06]

  New blog post: How Good Are GLM5.2 and Kimi-K3: Create Your Own Benchmark and Revisit Your Training Recipe.

• [2026.05]

  One paper, A Reward-Guided Dual-Phase Framework for Adaptive Inference-Time Reasoning, accepted to ACL 2026 (Findings)! Thanks to our interns and collaborators!

• [2026.04]

  New blog post: Designing Self-evolving Coding Agents for Terminal-Bench 2.0 — reaching 76.47% and top #7 on the TB2 leaderboard.

• [2026.02]

  New blog post: Revisiting DeepSeek’s 13 Research Papers — the complete technical evolution of DeepSeek base and reasoning models.

• [2026.01]

  TRAJECT-Bench: A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use accepted to ICLR 2026! Thanks to our interns and collaborators!