5 papers
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Yijun Lu, Rui Ye, Jiajun Wang +4
Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for…
Towards Recursive Self-Evolving Agentic Literature Retrieval
Yuwen Du, Tian Jin, Jing Kang +8
Scientific literature retrieval must understand complex search intents while preserving source authenticity. Traditional keyword and embedding-based systems return authentic source…
MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems
Rui Ye, Keduan Huang, Qimin Wu +17
LLM-based multi-agent systems (MAS) have demonstrated significant potential in enhancing single LLMs to address complex and diverse tasks in practical applications. Despite conside…
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users
Wenhao Wang, Mengying Yuan, Zijie Yu +5
The advancement of mobile GUI agents has opened new opportunities for automating tasks on mobile devices. Training these agents requires large-scale high-quality data, which is pro…