8 papers
AgenticScholar: Agentic Data Management with Pipeline Orchestration for Scholarly Corpora
Hai Lan, Tingting Wang, Zhifeng Bao +7
Managing the rapidly growing scholarly corpus poses significant challenges in representation, reasoning, and efficient analysis. An ideal system should unify structured knowledge m…
Adaptive Uncertainty-Aware Tree Search for Robust Reasoning
Zeen Song, Zihao Ma, Wenwen Qiang +2
Inference-time reasoning scaling has significantly advanced the capabilities of Large Language Models (LLMs) in complex problem-solving. A prevalent approach involves external sear…
SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models
Hamza Tahboub, Weiyan Shi, Gang Hua +1
Understanding social interactions from visual cues is a fundamental challenge for a socially competent AI. While powerful pre-trained vision-language models (VLMs) have shown remar…
WebATLAS: An LLM Agent with Experience-Driven Memory and Action Simulation
Jiali Cheng, Anjishnu Kumar, Roshan Lal +7
Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tu…
COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs
Peizheng Guo, Jingyao Wang, Wenwen Qiang +3
Despite Multimodal Large Language Models (MLLMs) having shown impressive capabilities, they may suffer from hallucinations. Empirically, we find that MLLMs attend disproportionatel…
Reward Model Generalization for Compute-Aware Test-Time Reasoning
Zeen Song, Wenwen Qiang, Siyu Zhao +2
External test-time reasoning enhances large language models (LLMs) by decoupling generation and selection. At inference time, the model generates multiple reasoning paths, and an a…