5 papers
Diagnosing Task Insensitivity in Language Agents
Jingyu Liu, Xiaopeng Wu, Kehan Chen +2
Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak. We identify a key source of this failure as task in…
DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs
Mingxuan Song, Yusen Huo, Bohan Zhou +5
Optimizing the advertiser's cumulative value of winning impressions under budget constraints poses a complex challenge in online advertising, under the paradigm of AI-Generated Bid…
Gradient Coupling: The Hidden Barrier to Generalization in Agentic Reinforcement Learning
Jingyu Liu, Xiaopeng Wu, Jingquan Peng +4
Reinforcement learning (RL) is a dominant paradigm for training autonomous agents, yet these agents often exhibit poor generalization, failing to adapt to scenarios not seen during…
Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction
Zhaopei Huang, Qifeng Dai, Guozheng Wu +7
With the rise of smart personal devices, service-oriented human-agent interactions have become increasingly prevalent. This trend highlights the need for personalized dialogue assi…
LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants
Haochen Huang, Jiahuan Pei, Yue Su +11
Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grained spatial reasoning and precis…