8 papers
CANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG
Hyojeong Yun, Jueun Kim, Wook-Shin Han
Multimodal RAG retrieves text, tables, images, and videos, but choosing a retrieval granularity does not determine how much context to retain within each item. Coarse units include…
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
Sungho Park, Wonjoong Kim, Jue Zhang +8
Automated harness optimization can substantially improve LLM agents by iteratively updating their prompts, tool interfaces, and control logic from execution feedback. However, exis…
Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
Jueun Kim, Sungho Park, Wook-Shin Han
A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a question is expressed often differs from the granularity at which corpus evidence is re…
AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces
Sungho Park, Wonjoong Kim, Rongyuan Tan +10
LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interactions and lead to overall task failure. Although external harnesses…
SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables
Sungho Park, Jueun Kim, Wook-Shin Han
Real-world Table-Text question answering (QA) tasks require models that can reason across long text and source tables, traversing multiple hops and executing complex operations suc…
HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval
Sungho Park, Joohyung Yun, Jongwuk Lee +1
Table-text retrieval aims to retrieve relevant tables and text to support open-domain question answering. Existing studies use either early or late fusion, but face limitations. Ea…
LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrieval
Joohyung Yun, Doyup Lee, Wook-Shin Han
Multimodal document retrieval aims to retrieve query-relevant components from documents composed of textual, tabular, and visual elements. An effective multimodal retriever needs t…
Failure is Feedback: History-Aware Backtracking for Agentic Traversal in Multimodal Graphs
Joohyung Yun, Doyup Lee, Wook-Shin Han
Open-domain multimodal document retrieval aims to retrieve specific components (paragraphs, tables, or images) from large and interconnected document corpora. Existing graph-based…