works on

From the 1 of 43 papers with an AI index.

most citedEdge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey

42 citations

Showing cs.AIShow all

7 papers · 1 filter

cs.AI2026

Understanding Cognition-Induced Risks in Agentic AI Systems

Guanchu Wang, Qinuo Li, Mengnan Du +2

Frontier agentic systems powered by large language models (LLMs) exhibit human-like patterns of cognition. As these systems become deeply integrated across different domains, their…

cs.AI20261 cited

Large Language Models in Mental Health: A Systematic Review of Applications, Innovations, and Ethical Challenges

Yisong Chen, Yifan Gao, Sijing Yu +2

We present a review on the applications of large language models (LLMs) in health, e.g., social media analysis, clinical conversational agents, therapy support tools, prompt engine…

cs.AI2026

RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning

Jinrui Liu, Bingyan Nie, Boyu Li +4

Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully. Despite the succe…

cs.AI2026

AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining

Hongjun Ding, Binqi Chen, Jinsheng Huang +6

Formula alpha mining, which generates predictive signals from financial data, is critical for quantitative investment. Although various algorithmic approaches-such as genetic progr…

cs.AI2026

SOM: Structured Opponent Modeling for LLM-based Agents via Structural Causal Model

Shiyue Cao, Pei Xu, Likun Yang +3

Accurately predicting opponents' behavior from interactions is a fundamental capability for large language model (LLM)-based agents in multi-agent and game-theoretic environments.…

cs.AI2026

Repeated Deceptive Path Planning against Learnable Observer

Shiyue Cao, Pei Xu, Likun Yang +6

We study the problem of deceptive path planning (DPP), where an agent aims to conceal its true destination from external observers. While existing work assumes static, non-learning…