1 citations · 1 across the 4 of their papers we have counts for
6 papers
DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution
Nan Jia, Wenxuan Shi, Jingqing Ruan +11
General-purpose agents are increasingly expected to perform professional analytics work, which requires sustained reasoning, iterative investigation, and reliable evidence. Trainin…
DivOPD: Spread Wide, Look Close for Asynchronous On-Policy Distillation of Multi-turn Agents
Hanyang Wang, Zeyuan Liu, Zhengyu Chen +7
On-policy distillation (OPD) trains student agents through teacher supervision on their own interactions with an environment. However, in asynchronous multi-turn training, arrival-…
CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data
Peiguang Li, Yongwei Zhou, Juncheng Diao +12
Open-web corpora curated via highly selective filters, such as FineWeb-Edu and DCLM, constitute the core of LLM pretraining data and have significantly advanced LLM performance. Ho…
BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents
Hanyang Wang, Weijieying Ren, Yuxiang Zhang +4
Stepwise group-based RL is an attractive way to train long-horizon LLM agents without a learned critic: it reuses multiple sampled rollouts to estimate local advantages. Its weakne…
Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning
Changyuan Tian, Zhicong Lu, Shuang Qian +8
To improve Multi-step Mathematical Reasoning (MsMR) of Large Language Models (LLMs), it is crucial to obtain scalable supervision from the corpus by automatically critiquing mistak…
LongCat-Flash Technical Report
Meituan LongCat Team, Bayan, Bei Li +179
We introduce LongCat-Flash, a 560-billion-parameter Mixture-of-Experts (MoE) language model designed for both computational efficiency and advanced agentic capabilities. Stemming f…