Autonomous agents, tool use, and agentic systems
![[2511.06448] When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2511.06448: When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Plat...
Abstract page for arXiv paper 2510.20728: Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems
Abstract page for arXiv paper 2510.06800: FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipe...
This paper explores dynamic decision-making under model misspecification, focusing on Thompson Sampling (TS) in Bayesian reinforcement le...
This paper presents a simplified transformer architecture tailored for small longitudinal cohort data, enhancing predictive performance w...
The paper presents Hybrid-Gym, a training environment designed to enhance coding agents' ability to generalize across various software en...
The paper presents SEMAS, a self-evolving multi-agent network designed for predictive maintenance in Industrial IoT, enhancing real-time ...
The paper discusses a framework for multi-round human-AI collaboration, emphasizing user-specified requirements to enhance decision quali...
This article explores the geometric relationships between independently trained multimodal contrastive models, revealing that an orthogon...
The paper presents a novel approach called Retrospective In-Context Learning (RICL) for enhancing temporal credit assignment in reinforce...
This paper explores the linear convergence of the Weighted Optimistic Gradient Descent-Ascent algorithm in multi-agent games with delayed...
The paper presents a novel grey-box method that integrates incomplete physics models into deep generative models, enabling the learning o...
This article presents a novel approach to episodic Markov decision process (MDP) planning by framing it as Bayesian inference over polici...
The paper presents LexiSafe, a novel offline safe reinforcement learning framework that employs a lexicographic safety-reward hierarchy t...
The paper introduces RLGT, a novel reinforcement learning framework designed for extremal graph theory, enhancing the application of RL i...
This article discusses the challenges of multi-expert learning in machine learning, highlighting how underfitting can occur when multiple...
This paper explores online learning models using improving agents, focusing on multiclass setups, budgeted agents, and bandit learners, e...
This paper introduces STDSH-MARL, a novel framework for human-centric traffic signal control that enhances multimodal transportation effi...
The paper introduces WS-GRPO, a method for improving rollout efficiency in language model training by providing correctness-aware guidanc...
This paper establishes a connection between pathwise and score-function gradient estimators in stochastic backpropagation, introducing a ...
The paper introduces Action Graph Policies (AGP) for multi-agent reinforcement learning, emphasizing the importance of action co-dependen...
The paper presents a novel approach to the multi-agent Lipschitz bandit problem, proposing a communication-free policy that maximizes col...
The paper presents Neuro-Symbolic Graph Generative Modeling (NSGGM), a framework that enhances molecule generation by integrating symboli...
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime