10 papers
Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training
Zhiyuan Wang, Shengcai Liu, Jiahao Wu +5
Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive. Evolution strategies (ES) enable memory-ef…
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
Jiahao Wu, Ning Lu, Shengcai Liu +6
Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance perfor…
Policy and World Modeling Co-Training for Language Agents
Ning Lu, Baijiong Lin, Shengcai Liu +9
Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do…
LLM-Driven Instance-Specific Heuristic Generation and Selection
Shaofeng Zhang, Shengcai Liu, Ning Lu +4
Combinatorial optimization problems are widely encountered in real-world applications. A critical research challenge lies in designing high-quality heuristic algorithms that effici…
OneForecast: A Universal Framework for Global and Regional Weather Forecasting
Yuan Gao, Hao Wu, Ruiqi Shu +11
Accurate weather forecasts are important for disaster prevention, agricultural planning, etc. Traditional numerical weather prediction (NWP) methods offer physically interpretable…
Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
Ning Lu, Shengcai Liu, Jiahao Wu +5
Large language models (LLMs) have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many com…