3 papers
cs.CL2025
From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement
Jianzhi Yan, Le Liu, Youcheng Pan +4
Chain-of-Thought (CoT) reasoning improves performance on complex tasks but introduces significant inference latency due to verbosity. We propose Multiround Adaptive Chain-of-Though…
cs.LG2025
GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning
Han Zhang, Ruibin Zheng, Zexuan Yi +16
As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing l…
cs.MA2025
MA-GTS: A Multi-Agent Framework for Solving Complex Graph Problems in Real-World Applications
Zike Yuan, Ming Liu, Hui Wang +1
Graph-theoretic problems arise in real-world applications like logistics, communication networks, and traffic optimization. These problems are often complex, noisy, and irregular,…