17 papers
Select-And-Extract: A Lightweight Plugin for Retrieval-Augmented Generation
Chenming Tang, Jiawei Han
Retrieval-augmented generation (RAG) for language model (LM) systems fundamentally has two failure modes: retrieval failure and reading failure. The former fails to recall the righ…
MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry
Joey Chan, Wonbin Kweon, Ashley Shin +4
Large language models (LLMs) have shown promise for molecular property prediction, but their ability to reason over chemical structures remains limited, as molecular representation…
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…
Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
Pengcheng Jiang, Judith Yue Li, Moonkyung Ryu +8
Many modern retrieval problems are set-valued: given a broad intent, the system must return a collection of results that optimizes higher-order properties (e.g., diversity, coverag…
Structure-Augmented Reasoning Generation
Jash Rajesh Parekh, Pengcheng Jiang, Jiawei Han
Recent advances in Large Language Models (LLMs) have significantly improved complex reasoning capabilities. Retrieval-Augmented Generation (RAG) has further extended these capabili…