14 papers
Counterexamples to the total-current Hohenberg-Kohn conjecture
Andre Laestadius, Mihály A. Csirik
The total-current Hohenberg-Kohn conjecture asserts that the ground-state particle density and total current determine the scalar potential up to an additive constant and the vecto…
Agents' Last Doubt: Knowing When to Act and When to Step Back in Tool-Using Agents
Qisai Liu, Qingyue Jiao, Bangwei Guo +7
Tool-using LLM agents repeatedly face decision points under uncertainty, choosing between autonomous action, additional information gathering, and human escalation. These decisions…
Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory
Minghao Guo, Qingyue Jiao, Xiujin Liu +77
Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities…
ReSolve: Reusing Candidate Reasoning through Selective Generative Moderation
Bangji Yang, Jiajun Fan, Hongba Ma +7
Sampling multiple solutions spends computation on intermediate deductions and unfinished arguments as well as final answers. We introduce ReSolve, a training-free inference procedu…
Agents in the Large: Perception-Centered Architecture for Persistent Agents
Shihan Dou, Haoxiang Jia, Shichun Liu +14
Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling agents to reason and act in i…
OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents
Xinying Cai, Minghao Guo, Jiahe Liu +7
Large language models are increasingly used to read markets, assess risk, and allocate capital. However, reported results for LLM trading agents can be inflated by look-ahead leaka…
Trust or Abstain? A Self-Aware RAG Approach
Xi Zhu, Ziqi Wang, Kai Mei +5
Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge conflicts when retrieved contextual…
RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing
Ziqi Wang, Xi Zhu, Shuhang Lin +3
Retrieval-augmented generation (RAG) has evolved into a family of paradigms with distinct performance profiles and resource demands, turning paradigm selection into a multi-criteri…
AEL: Evolving Agent Harness in Open-Ended Environments
Wujiang Xu, Jiaojiao Han, Minghao Guo +4
LLM Agents Harnesses are hand-designed and stay fixed, so agents accumulate experience but never learn how to use it: which memories to retrieve, when retrieved evidence is mislead…
Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Data
Minghao Guo, Ziyi Ye, Wujiang Xu +3
Large Language Models (LLMs) have demonstrated remarkable human-like capabilities, yet their ability to replicate a specific individual remains under-explored. This paper presents…
TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation
Bangde Du, Minghao Guo, Songming He +8
Large Language Models (LLMs) are exhibiting emergent human-like abilities and are increasingly envisioned as the foundation for simulating an individual's communication style, beha…
Node-as-Agent: Graph Agentic Network
Minghao Guo, Xi Zhu, Qingyue Jiao +7
Graph Neural Networks (GNNs) have achieved remarkable success in graph-based learning by propagating information among neighbor nodes via predefined aggregation mechanisms. However…
From Aggregation to Selection: User-Validated Distributed Social Recommendation
Jingyuan Huang, Dan Luo, Zihe Ye +3
Social recommender systems facilitate social connections by identifying potential friends for users. Each user maintains a local social network centered around themselves, resultin…
LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models
Xi Zhu, Haochen Xue, Ziwei Zhao +7
Text-Attributed Graphs (TAGs), where each node is associated with text descriptions, are ubiquitous in real-world scenarios. They typically exhibit distinctive structure and domain…