AI Agents

NeuBird AI Raises $19.3 Million To Scale Agentic AI

[2511.06448] When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms

Abstract page for arXiv paper 2511.06448: When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Plat...

[2510.20728] Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems

Abstract page for arXiv paper 2510.20728: Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems

[2506.11798] Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models

This paper explores the use of Large Language Models (LLMs) to simulate voting behavior in the European Parliament through persona-driven...

[2505.17508] On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning

This paper presents a unified framework for KL-regularized policy gradient algorithms aimed at enhancing reasoning in large language mode...

[2503.04121] Simple Self Organizing Map with Vision Transformers

This paper explores the integration of Self-Organizing Maps (SOMs) with Vision Transformers (ViTs) to enhance performance on small datase...

[2502.03752] Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning

This paper presents Self-Improving Skill Learning (SISL), a novel approach to enhance skill-based meta-reinforcement learning by refining...

[2412.18362] Point-DeepONet: Predicting Nonlinear Fields on Non-Parametric Geometries under Variable Load Conditions

Point-DeepONet introduces a novel approach for predicting nonlinear fields in engineering, leveraging deep learning to enhance efficiency...

[2412.02039] Multi-View 3D Reconstruction using Knowledge Distillation

This paper presents a knowledge distillation approach for Multi-View 3D reconstruction, utilizing a teacher-student model framework to en...

[2602.00307] Autonomous Data Processing using Meta-Agents

The paper presents a novel framework, Autonomous Data Processing using Meta-Agents (ADP-MA), which enhances data processing pipelines thr...

[2601.15599] Autonomous Business System via Neuro-symbolic AI

The paper presents AUTOBUS, an Autonomous Business System that integrates LLM-based AI agents with predicate-logic programming to enhance...

[2601.07463] Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learning

This paper presents a novel Local-to-Global (LOGO) world model for offline multi-agent reinforcement learning (MARL), improving policy ge...

[2511.17673] Bridging Symbolic Control and Neural Reasoning in LLM Agents: Structured Cognitive Loop with a Governance Layer

This article introduces the Structured Cognitive Loop (SCL) architecture for large language model (LLM) agents, addressing key architectu...

[2510.19771] Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents

The paper presents PROBE, a new framework for measuring proactive problem-solving capabilities in LLM agents, highlighting their limitati...

[2508.12026] Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems

The paper presents Bongard-RWR+, a dataset designed to enhance fine-grained visual reasoning in Bongard Problems using real-world images ...

[2510.00167] Drones that Think on their Feet: Sudden Landing Decisions with Embodied AI

The paper discusses how embodied AI enables drones to make adaptive landing decisions in real-time, enhancing their resilience and safety...

[2505.16928] Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning

This article presents the $ ext{∞-THOR}$ framework for long-horizon embodied tasks, focusing on enhancing long-context reasoning in AI th...

[2505.08021] The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order Logic

This paper explores the relationship between Bounded Graph Neural Networks (GNNs) and fragments of first-order logic, providing insights ...

[2503.17338] Capturing Individual Human Preferences with Reward Features

The paper discusses a new approach to modeling individual human preferences in reinforcement learning, emphasizing the need for adaptive ...

[2502.13062] AI-Assisted Decision Making with Human Learning

This paper explores AI-assisted decision-making, focusing on how algorithms can enhance human learning through feature selection, balanci...

[2410.13957] Goal Inference from Open-Ended Dialog

The paper discusses a method for embodied AI agents to infer user goals from open-ended dialogues using Large Language Models (LLMs), emp...

[2412.18899] GAI: Generative Agents for Innovation

The paper explores GAI, a framework for generative agents that enhances collective reasoning to foster innovation, evaluated through a ca...

[2602.17658] MARS: Margin-Aware Reward-Modeling with Self-Refinement

The paper presents MARS, a novel margin-aware reward modeling framework that enhances training efficiency by focusing on ambiguous prefer...