8 papers
Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
Guanghui Min, Liang Wu, Mayank Darbari +2
Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary empirical study, we show that…
Mosaic: Towards Efficient Training of Multimodal Models with Spatial Resource Multiplexing
Yanbo Wang, Yuxuan Wang, Chen Chen +6
With the wide adoption of Multimodal Models (MMs) in real-world scenarios, it is significant to efficiently train emerging MMs that exhibit increasingly complex module architecture…
SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation
Zaiyi Zheng, Guanghui Min, Yaochen Zhu +4
Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short…
AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering
Taolin Zhang, Dongyang Li, Chen Chen +5
Despite substantial advances in large language models (LLMs), generating factually consistent responses for knowledge-intensive question answering remains challenging. These diffic…
Taming "Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution
Taolin Zhang, Pukun Zhao, Qizhou Chen +5
Recent advancements in LLM-based multi-agent systems have demonstrated remarkable collaborative capabilities across complex tasks. To improve overall efficiency, existing methods o…
GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources
Boxiao Du, Boning Huangfu, Yizhou Luo +5
Large Language Models (LLMs) play a critical role in emerging agentic applications, where the timely completion of each entire inference is critical. Meanwhile, agentic LLM inferen…