10 papers
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Pengcheng Jiang, Zhiyi Shi, Kelly Hong +5
Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which c…
Learning to Predict Future-Aligned Research Proposals with Language Models
Heng Wang, Pengcheng Jiang, Jiashuo Sun +4
Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and sou…
Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
Jiashuo Sun, Jimeng Shi, Yixuan Xie +10
Retrieval-Augmented Generation (RAG) has become a standard approach for knowledge-intensive question answering, but existing systems remain brittle on multi-hop questions, where so…
Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi +31
Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learnin…
Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning
Chongjie Si, Zhiyi Shi, Shifan Zhang +3
Large language models demonstrate impressive performance on downstream tasks, yet they require extensive resource consumption when fully fine-tuning all parameters. To mitigate thi…
Virtual Multiplex Staining for Histological Images using a Marker-wise Conditioned Diffusion Model
Hyun-Jic Oh, Junsik Kim, Zhiyi Shi +5
Multiplex imaging is revolutionizing pathology by enabling the simultaneous visualization of multiple biomarkers within tissue samples, providing molecular-level insights that trad…