Multi-agent systems
84 notes, newest first. Includes the vault tags multi-agent systems, multi-agent, collaboration.
Cogentic: Multi-Agent Orchestration for Automated Proof Discovery
The preprint describes an orchestrator that assigns independent provers to competing proof directions, uses specialized adversarial verification components, and promotes confirmed intermediate results into a persistent…
Multi-agent Scaling Across Disjunctive and Compensatory Tasks
The preprint introduces a taxonomy of group tasks and analyzes multi-agent LLM scaling on disjunctive and compensatory tasks. Across 13 open-weight models and teams of up to 30 agents, the abstract reports that…
How does Adversarial Influence Scale in Multi-Agent Systems?
The preprint studies deception in multi-agent deliberation. Its abstract reports that susceptibility depends on the proportion of deceivers rather than total group size, that defection rises approximately linearly with…
Emergent Collusion in Long-Horizon LLM Agent Interaction
The study examines two agents repeatedly completing tasks, sharing logs, verifying each other's work, and receiving rewards under a protocol whose compliance conflicts with reward maximization. The abstract reports…
Language-model groups overstate consensus when replaying human deliberation on a reasoning task
The preprint replays 100 held-out human Wason groups with matched LLM agent groups, using belief-anchored agents and shared scoring code. It reports that consensus estimates depend on participation and final-state…
Agentic Societies Need a Social Harness
The authors study collections of agents operating across trust boundaries for different principals. They report that honest agents can fail with current messaging primitives, while faulty or malicious agents can stall…
DentAgent: Evidence-Centric Multi-Agent Coordination for Multimodal Dental Reasoning
A new system called DentAgent is introduced that aims to improve the accuracy and reliability of dental assessments by integrating various forms of evidence from different modalities. The system uses an…
When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding
The authors studied how AI coding agents coordinate while working on programming tasks. They developed a method to measure this coordination by representing each run as a network with nodes (agents and files) connected…
Automating and Scaling Behavioral Scientific Research on AI Agents
The paper presents AEROBAT, a multi-agent system intended to automate parts of behavioral research on AI agents, from hypothesis generation through experiments, assessment, analysis, and reporting.
Multi-Agent AI Safety as an Institutional Design Problem
The paper discusses AI safety as an institutional design problem in multi-agent systems. The research focuses on understanding which parts of an AI institution ensure safety and how they do it. The study involves a…
NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation
Researchers propose NeuroRefiner, a multi-agent system for improving the accuracy of 3D neuron segmentation in fluorescence microscopy. The system addresses challenges posed by the sparse and elongated morphology of…
The Politician, the Liar, and the Obedient Worker: Emerging Behavior of LLM Agents in Hierarchical Games
A study introduces a new game called Hierarchical Game (HG) to test LLMs behavior in multi-agent organizations. The research finds distinct behavioral profiles among six frontier models, with some promising and lying…
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
CoPlan is a new AI system designed to help with care planning for clinicians, patients, caregivers, and care teams. It allows stakeholders to inspect, challenge, and revise plans if they conflict with clinical…
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
The paper introduces CoPlan, a new AI system designed to aid in care planning. CoPlan allows various stakeholders like clinicians, patients, and caregivers to collaborate on complex decisions by generating potential…
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment
Researchers propose NSF-HRPT, a framework that uses a Neural Semantic Field (NSF) to model scene semantics, trajectory predictions, and probabilistic Time-to-Collision (TTC) distributions from simulation data. During…
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
The study investigates how effective relaying key-value caches between multi-agent language models is, particularly when the receiver does not need the sender's private information. The research shows that when the…
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
The paper introduces MANTA, a framework for adapting communication structures in multi-agent systems during inference time. This allows for more efficient problem solving by enabling agents to adjust their roles…
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
The paper introduces MANTA, a framework for Multi-Agent Network Topology Adaptation that allows communication structures in large language model-based multi-agent systems to evolve during inference time. This…
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
The paper introduces MANTA, a framework for Multi-Agent Network Topology Adaptation that allows communication structures in large language model-based multi-agent systems to evolve during deployment. The goal is to…
PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks
Researchers present PAIChecker, a system designed to detect misalignment between Pull Requests (PRs) and Issues in SWE-bench-like benchmarks used for evaluating Large Language Models (LLMs). The system identifies…
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
Researchers have introduced a new framework for ontology matching called AgentMap. This framework can simultaneously discover both equivalent and subsuming mappings in ontologies, which existing systems cannot do. The…
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
Researchers have developed a method to evaluate if latent channels in large language models effectively communicate task-relevant information in multi-agent systems. The study applies this method to Qwen3 and Qwen3-8B…
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
Researchers introduce a method to study how latent channels in multi-agent systems, which transmit information without using text, impact the receiver's performance. They apply this method to Qwen3-4B and Qwen3-8B on…
Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
Researchers introduce a new method called CE-CM (Capability Estimation via Contextual Models) to help autonomous agents collaborate effectively with novel and diverse partners in a multi-task setting. The method infers…
Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
Researchers propose an approach called CE-CM (Capability Estimation via Contextual Models) to help autonomous agents collaborate with diverse partners in a multi-task setting. The method infers task-invariant…
Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections
The paper introduces a new deep reinforcement learning architecture called Master-Agent Proto-plan System (MAPS) for coordinating autonomous vehicles at unsignalized intersections. The MAPS system uses a centralized…
Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections
Researchers proposed a new system called Master-Agent Proto-plan System (MAPS) for coordinating autonomous vehicles at unsignalized intersections using deep reinforcement learning. MAPS outperformed state-of-the-art…
Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections
Researchers present MAPS, a deep reinforcement learning architecture for coordinating autonomous vehicles at unsignalized intersections. The system uses a central Master agent that generates a global coordination…
Explainable Belief Harmonization under Dynamic Epistemic Partitions
This paper presents a formal framework for handling dynamic changes in epistemic partitions (groups of agents with shared information) during the execution of multi-agent systems. The framework uses a hybrid approach…
GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG
The authors present GRADRAG, a framework for improving Retrieval-Augmented Generation (RAG) systems by coordinating updates across multiple agents in the pipeline. The system uses feedback from an Evaluator to update…
GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG
The paper introduces GRADRAG, a framework for improving Retrieval-Augmented Generation (RAG) systems by coordinating improvements across different components of the pipeline. It uses feedback from an Evaluator to…
GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG
The paper introduces GRADRAG, a framework that improves Retrieval-Augmented Generation (RAG) systems by coordinating improvements across the pipeline. Instead of optimizing components in isolation, GRADRAG models the…
pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory Development
The paper introduces pAI-Econ-claude, a multi-agent architecture that helps in AI-assisted economic theory development. The system uses a gated, human-in-the-loop approach to coordinate agents and ensure the final…
pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory Development
A new multi-agent architecture, named pAI-Econ-claude, was proposed for AI-assisted economic theory development. This architecture uses a gated human-in-the-loop system to ensure reliability in tasks where no machine…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study comparing direct exposure to a dangerous objective versus multi-agent mediation using OpenAI's gpt-5.6-sol model reveals that direct exposure leads to advice contrary to the target, while mediated exposure…
BrainPilot: Automating Brain Discovery with Agentic Research
BrainPilot is a multi-agent system designed to accelerate brain science research by integrating evidence from various scales, modalities, and disciplines. It uses a unified brain science knowledge base containing over…
Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
Researchers present a multi-agent framework that simulates political coalition formation using Large Language Models (LLMs). The framework combines Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO)…
Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
Researchers present a multi-agent framework using Large Language Models (LLMs) to simulate and audit political coalition formation in elections. The framework combines Supervised Fine-Tuning (SFT), Direct Preference…
Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
Researchers have developed a multi-agent framework using Large Language Models (LLMs) to simulate coalition formation in political elections. The framework combines Supervised Fine-Tuning, Direct Preference…
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
The paper introduces SearchOS, a system that aims to improve the efficiency of open-domain information seeking for information-seeking agents. It struggles with tracking task progress as interaction histories grow and…
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
Researchers introduce SearchOS, a system-level framework designed to improve the efficiency of multi-agent information-seeking systems. By making search progress explicit and persistent, it helps prevent repetitive…
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
The paper introduces SearchOS, a system-level multi-agent framework designed to improve the quality and completeness of search results in open-domain information-seeking tasks. The framework addresses the issue of…
Early Adoption of Agentic Coding Tools by GitHub Projects
The paper investigates the early adoption of automated coding tools by GitHub projects. It found that while intensive adoption is concentrated in a few projects, smaller projects tend to have higher participation…
Early Adoption of Agentic Coding Tools by GitHub Projects
This research investigates the adoption and management of agentic coding tools in software development on GitHub. The study analyzes 25,264 agentic pull requests from 2,361 popular repositories to understand (1) how…
The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous Commerce
The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) model is introduced in this research, aiming to account for the effects of autonomous AI agents on traditional customer loyalty paradigms. The…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
A new multi-agent system named Pythia was developed for automatically and independently creating and optimizing clinical concept extraction prompts without manual engineering or fine-tuning. The study compared Pythia…
Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities
Researchers present Bulkhead, an automated framework that uses large language models and formal methods to detect and fix container escape vulnerabilities called path traversal (PaTra) vulnerabilities. These…
Unveiling Complex Collective Behaviors from Simple Rewards
Researchers have developed a new method called the Agent Response Map (ARM) to help understand how simple rewards can lead to complex behaviors in multi-agent reinforcement learning (MARL). The ARM reveals that robots…
Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination
Researchers present G-Frame, an adaptive multi-agent framework that reduces hallucinations in lightweight large language models used in rule-based scientific domains. The framework is based on Bayesian and team game…
WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
WebSwarm is a framework that uses multiple language model-based search agents to perform complex, deep-and-wide web searches. It aims to overcome the limitations of single ReAct-style agents by dynamically…
WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
The paper proposes a new framework called WebSwarm for multi-agent search systems. This system aims to improve deep-and-wide web searches by dynamically creating search nodes that can delegate tasks recursively and…
WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
Researchers propose a new framework called WebSwarm for deep and wide web searches using large language models (LLMs). The framework aims to improve the ability of single agents to handle complexity and coverage…
WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
The paper presents a new framework called WebSwarm for web search using multiple agents. This system aims to overcome the limitations of single agents by simultaneously handling depth and coverage, improving recursive…
Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
The research discusses the study of multi-agent AI control in real-world scenarios where multiple agents operate over shared infrastructure. The paper introduces FakeLab, a synthetic AI-lab codebase used to evaluate…
GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
The research presents a new coding system called Graph-as-Policy (GaP) for robots to work reliably in commercial and industrial applications. GaP combines interpretable robot programming with the adaptability of…
OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement
The researchers have developed a multi-agent framework called OptiAgent that can take a natural language description of an Operations Research problem and produce a mathematically formulated solution along with…
OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement
The authors propose OptiAgent, a multi-agent framework that takes a natural language description of an Operations Research problem and produces a solver-ready mathematical formulation and executable code. The…
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting
The study examines the performance of human-AI collaboration in forecasting using real-money prediction markets as a benchmark. It finds that the effectiveness of this collaboration is dependent on a specific type of…
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting
A study using real-money prediction market Polymarket finds that the performance of human-AI collaboration in forecasting depends on specific forms of human capital such as perspective-taking, intellectual humility…
QFedAgent: Quantum-Enhanced Personalized Federated Learning for Multi-Agent Activity Recognition
The paper proposes QFedAgent, a new approach for multi-agent activity recognition in federated learning. It uses a hybrid quantum-classical framework and a variational quantum circuit fusion module that models…
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development
The researchers proposed UA-ChatDev, an uncertainty-aware multi-agent software development framework to improve the reliability of autonomous multi-agent software development. The framework uses a lightweight…
What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates
Researchers studied how language models (LLMs) behave in socially structured settings, where role, audience, and relationships can influence what the LLM says publicly versus privately. They found that when there's an…
MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
The paper introduces MECoBench, a new system for testing the collaboration abilities of multimodal large language models in visually grounded environments. The authors conduct extensive experiments with various MLLMs…
TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models
Researchers propose a multi-agent system (MAS) called TreeAgent to automate bias labeling in forestry via expert decision trees and Vision-Language Models (VLMs). The MAS aims to reduce the need for human annotation…
TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models
Researchers have proposed a multi-agent system that uses expert decision trees and Vision-Language Models (VLMs) to automate the bias classification in tree height in forestry remote sensing. The system mitigates VLM…
AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
The paper proposes AgentsNet, a new benchmark for multi-agent reasoning. This benchmark is designed to measure the ability of multi-agent systems to collaborate effectively and leverage their network topology. The…
Latent Actions from Factorized Transition Effects under Agent Ambiguity
The research introduces Observed Transition Factorization (OTF), a method to decompose transitions in multi-object or distracting scenes into reusable transition primitives. These primitives are used to form…
Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing
A new routing architecture called ANTAP (Automatic Non-Textual Agent Picker) was introduced in this research. It aims to address security vulnerabilities in multi-agent systems by discarding indirect proxies and…
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
The paper introduces a framework called Mesa to prioritize the security of vulnerable communication channels in multi-agent systems (MAS). The framework uses graph-theoretic metrics and dynamic probes to rank which MAS…
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
The paper presents Mesa, a framework for prioritizing vulnerable communication channels in multi-agent systems (MAS). Mesa uses graph-theoretic metrics and dynamic probes to identify the edges most likely to affect the…
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
In this research paper titled 'MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems', the authors propose a framework called Mesa to prioritize and secure communication channels in…
Translating Natural Language to Strategic Temporal Specifications via LLMs
Researchers have developed a framework for translating Natural Language descriptions of strategic requirements into well-formed ATL/ATL* formulas using Large Language Models (LLMs). They created and validated a novel…
Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts
The authors present a framework for analyzing dialogue in collaborative problem-solving contexts, particularly focusing on human-AI and multi-agent collaboration. The framework addresses limitations in current…
Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts
The authors present a framework for analyzing dialogue in collaborative problem-solving contexts, especially in human-AI and multi-agent collaboration. The framework aims to understand the emerging dynamics of these…
Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts
Researchers present a framework for analyzing dialogues during collaborative problem-solving tasks involving human-AI and multi-agent interactions. The framework aims to optimize and evaluate these partnerships by…
Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound
Researchers propose a method called Multi-Agent Goal Recognition with Branch-and-Bound (MAGR-BB) to infer the goals of multiple agents in real applications like drone surveillance and collaborative robotics, where only…
Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound
The paper introduces Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound (MAGR-BB), a method for inferring which agents are working together and what each…
Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound
The paper presents Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound (MAGR-BB), a method to infer which agents in a multi-agent system are working…
Probabilistic Agents in Deterministic Audits: Evaluating Multi-Agent Systems for Automated Audits Based on the German IT-Grundschutz
This research paper presents a Multi-Agent System (MAS) architecture with Hybrid Retrieval Augmented Generation (HybridRAG) for partially automating IT-Grundschutz certification, a German standard for IT security. The…
Probabilistic Agents in Deterministic Audits: Evaluating Multi-Agent Systems for Automated Audits Based on the German IT-Grundschutz
This research presents the implementation and evaluation of a Multi-Agent System (MAS) architecture combined with Hybrid Retrieval Augmented Generation (HybridRAG) for partially automating IT-GS certification, which is…
Governed Shared Memory for Multi-Agent LLM Systems
The paper proposes a solution for managing shared knowledge in multi-agent language model (LLM) environments. The authors identify four failure modes and introduce four primitives: scoped retrieval, temporal…
Governed Shared Memory for Multi-Agent LLM Systems
The paper discusses the challenges in managing shared knowledge in multi-agent language models (LLMs) environments and proposes solutions to prevent four failure modes: unauthorized leakage, stale propagation…
Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity
Researchers propose a new method to enhance large language models while maintaining privacy in sensitive scenarios. The method uses a multi-agent framework that sanitizes retrieved content through semantic rewriting…
Dynamic multi-agent deep reinforcement learning-based pricing and incentivization approach in multimodal transportation networks
A study proposes a multi-agent deep reinforcement learning framework to coordinate shared mobility services (SMSs) and public transport in multimodal transportation systems. The framework aims to improve efficiency…
