6 papers
ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agents
Yilun Yao, Shan Huang, Elsie Dai +5
Large language models are increasingly deployed as research agents for deep search and long-horizon information seeking, yet their performance often degrades as interaction histori…
EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices
Mengyun Liu, Shanshan Huang, Jianan Jiang
Large Action Models (LAMs) have shown immense potential in autonomous navigation by bridging high-level reasoning with low-level control. However, deploying these multi-billion par…
From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning
Hang Du, Jiayang Zhang, Guoshun Nan +8
Multi-image Interleaved Reasoning aims to improve Multi-modal Large Language Models (MLLMs) ability to jointly comprehend and reason across multiple images and their associated tex…
ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII Art
Qi Jia, Xiang Yue, Shanshan Huang +5
Perceiving visual semantics embedded within consecutive characters is a crucial yet under-explored capability for both Large Language Models (LLMs) and Multi-modal Large Language M…
TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data
Xiang Huang, Jiayu Shen, Shanshan Huang +3
Semantic parsing, which converts natural language questions into logic forms, plays a crucial role in reasoning within structured environments. However, existing methods encounter…
QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction
Xiang Huang, Sitao Cheng, Shanshan Huang +4
Employing Large Language Models (LLMs) for semantic parsing has achieved remarkable success. However, we find existing methods fall short in terms of reliability and efficiency whe…