10 papers
Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability
Xianyou Li, Weiran Yan, Yichao Wu +4
Failure-aware observability diagnoses wasted computation in multi-agent LLM systems before final-answer evaluation can explain what went wrong. We propose a trace-based framework f…
Architecture Matters More Than Scale: A Comparative Study of Retrieval and Memory Augmentation for Financial QA Under SME Compute Constraints
Jianan Liu, Jing Yang, Xianyou Li +4
The rapid adoption of artificial intelligence (AI) and large language models (LLMs) is transforming financial analytics by enabling natural language interfaces for reporting, decis…
Recursive Multi-Agent Trading System: Iterative Optimized Portfolio Strategy Under Geopolitical Uncertainty
Jing Yang, Yichao Wu, Jianan Liu +4
Recursive Multi-Agent Trading System (RMATS) integrates four specialized agents -- Sentiment, Report, Analysis, and Risk -- coordinated through a recursive Manager Agent with itera…
Stop Wandering: Efficient Vision-Language Navigation via Metacognitive Reasoning
Xueying Li, Feng Lyu, Hao Wu +3
Training-free Vision-Language Navigation (VLN) agents powered by foundation models can follow instructions and explore 3D environments. However, existing approaches rely on greedy…
TA-Mem: Tool-Augmented Autonomous Memory Retrieval for LLM in Long-Term Conversational QA
Mengwei Yuan, Jianan Liu, Jing Yang +4
Large Language Model (LLM) has exhibited strong reasoning ability in text-based contexts across various domains, yet the limitation of context window poses challenges for the model…
Tiny-Critic RAG: Empowering Agentic Fallback with Parameter-Efficient Small Language Models
Yichao Wu, Penghao Liang, Yafei Xiang +5
Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) to mitigate factual hallucinations. Recent paradigms shift from static pipelines to Modular and Agentic RA…
DynaRAG: Bridging Static and Dynamic Knowledge in Retrieval-Augmented Generation
Penghao Liang, Mengwei Yuan, Jianan Liu +4
We present DynaRAG, a retrieval-augmented generation (RAG) framework designed to handle both static and time-sensitive information needs through dynamic knowledge integration. Unli…
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Xingjun Ma, Yixu Wang, Hengyuan Xu +18
The rapid evolution of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has driven major gains in reasoning, perception, and generation across language and…
Legal Document Summarization: Enhancing Judicial Efficiency through Automation Detection
Yongjie Li, Ruilin Nong, Jianan Liu +1
Legal document summarization represents a significant advancement towards improving judicial efficiency through the automation of key information detection. Our approach leverages…
Adaptive Learning Systems: Personalized Curriculum Design Using LLM-Powered Analytics
Yongjie Li, Ruilin Nong, Jianan Liu +1
Large language models (LLMs) are revolutionizing the field of education by enabling personalized learning experiences tailored to individual student needs. In this paper, we introd…