8 papers
Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems
Xin Xu, Ke Cheng, Hao Wang +11
Improving an agent through successive revisions requires balancing exploration and evaluation under a limited budget. A narrow search can miss useful sequences of edits, while full…
From Head to Tail: Asymmetric Knowledge Transfer in Long-tail Recommendation with Generative Semantic IDs
Chenyi Yan, Ruocong Tang, Xing Fang +3
Long-tail recommendation in real-world e-commerce platforms remains challenging due to severe data imbalance. Existing methods often struggle to combine content-based multimodal fe…
UniVA: Unified Value Alignment for Generative Recommendation in Online Advertising at Tencent
Xinxun Zhang, Yuling Xiong, Yangru Huang +14
Generative Recommendation (GR) reformulates recommendation as next-token generation over item Semantic IDs (SIDs) and has shown promise in industrial applications. However, extendi…
S-GRec: Personalized Semantic-Aware Generative Recommendation with Asymmetric Advantage
Jie Jiang, Hongbo Tang, Wenjie Wu +6
Generative recommendation models sequence generation to produce items end-to-end, but training from behavioral logs often provides weak supervision on underlying user intent. Altho…
Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation
Jie Jiang, Yangru Huang, Zeyu Wang +4
Generative recommendation via autoregressive models has unified retrieval and ranking into a single conditional generation framework. However, fine-tuning these models with Reinfor…
OpAgent: Operator Agent for Web Navigation
Yuyu Guo, Wenjie Yang, Siyuan Yang +12
To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely…
Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates
Yusen Huo, Changping Wang, Yangru Huang +2
Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures. We show that repeated reuse can turn this useful signa…
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLM
Codefuse, Ling Team, : +30
Recent advancements in code large language models (LLMs) have demonstrated remarkable capabilities in code generation and understanding. It is still challenging to build a code LLM…