1 citations · 1 across the 5 of their papers we have counts for
5 papers
Belayer: Efficient Fault Tolerance for LLM Agentic RL Training
Jiecheng Zhou, Qinghao Hu, Peng Sun +2
Large language model (LLM) agents are increasingly trained with reinforcement learning in long-horizon, sandboxed environments. Unlike conventional RL, agentic RL couples GPU-inten…
MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement
Lushi Pu, Weiming Zhang, Xinheng Xie +7
Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4. However, faithful formalizatio…
MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis
Lushi Pu, Weiming Zhang, Xinheng Xie +6
Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing formal benchmarks remain limited in both mathematical coverage and difficulty. Mo…
RL in the Wild: Characterizing RLVR Training in LLM Deployment
Jiecheng Zhou, Qinghao Hu, Yuyang Jin +7
Large Language Models (LLMs) are now widely used across many domains. With their rapid development, Reinforcement Learning with Verifiable Rewards (RLVR) has surged in recent month…
Towards Efficient Pre-training: Exploring FP4 Precision in Large Language Models
Jiecheng Zhou, Ding Tang, Rong Fu +8
The burgeoning computational demands for training large language models (LLMs) necessitate efficient methods, including quantized training, which leverages low-bit arithmetic opera…