11 papers
InfoPO: Information-Driven Policy Optimization for User-Centric Agents
Fanqi Kong, Jiayi Zhang, Mingyi Deng +3
Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downstream decisions. However, current multi-t…
Adaptive Punishment for Cooperation in Mixed-Motive Games
Min Tang, Fanqi Kong, Linyuan Lü +1
Mixed-motive scenarios are ubiquitous in real-world multi-agent interactions, where self-interested agents often defect for immediate rewards, overlooking the potential of altruist…
Scalable Environments Drive Generalizable Agents
Jiayi Zhang, Fanqi Kong, Guibin Zhang +7
Generalizable agents should adapt to diverse tasks and unseen environments beyond their training distribution. This position paper argues that such generalization requires environm…
When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression
Ruijie Zhang, Haozhe Liang, Da Chang +4
Long-context LLM inference is bottlenecked by the memory and bandwidth cost of reading large KV caches during decoding. KV compression reduces this cost by keeping only part of the…
SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning
Fanqi Kong, Weiqin Zu, Xinyu Chen +3
Understanding social interaction, which encompasses perceiving numerous and subtle multimodal cues, inferring unobservable mental states and relations, and dynamically predicting o…
Aegis: Automated Error Generation and Attribution for Multi-Agent Systems
Fanqi Kong, Ruijie Zhang, Huaxiao Yin +7
Large language model based multi-agent systems (MAS) have unlocked significant advancements in tackling complex problems, but their increasing capability introduces a structural fr…