AI & Machine Learning · Computer Science & AI
Multiagent Systems
The newest papers in Multiagent Systems that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
829 papers, from 4 September 2026 to 5 November 2026: 829 arXiv preprints.
Get the few papers worth your time in Multiagent Systems every morning.
Follow Multiagent Systems and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 23
Scalar Communication via Random Direction Refreshing for Distributed Optimization
Distributed optimization over networks requires agents to repeatedly exchange decision variables with their neighbors.Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness
We study adversarial multiplayer bandits with $K$ arms and $2\le m<K$ labeled players, without collision information, shared randomness, or an external communication channel.Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement
Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing zero trust introduces significant challenges in safety, reliability, and…Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System
A language model may behave safely in a single-agent evaluation yet produce vulnerable code when its context suggests that it is part of a multi-agent system.Who Keeps the Gains from Personal AI Assistants? Seller Adaptation and the Unassisted in a Language-Model Market Simulation
Personal AI assistants are beginning to transact for consumers, and early adopters capture real savings.Priority Coordination Games: Hodge Decomposition and a Sharp Design Limit
In decentralised priority coordination, agents announce priority levels and a shared resource serves them in decreasing order, as at an unsignalised intersection; the levels form the decision layer…Parallelism or Concession? Concurrency-Aware Procurement Negotiation for Agentic Commerce
Agentic buyers can cheaply fork a procurement task into many parallel negotiations, but concurrency is not free: every thread consumes resources, and simultaneous agreements create cancellation and…Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help
Recent work on multi-agent LLM systems reaches sharply different conclusions: some results show that a single agent with the same information and compute should dominate a delegated system, others…Feedback Dominance Analysis for Pursuit-Evasion Games on Graphs
This work identifies the dominance regions for discrete, simultaneous-move pursuit-evasion games on graphs.GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories
GAMBIT is an opening chess move in which a player sacrifices a piece, typically a pawn, to gain a positional advantage later in the game.Visual Swarm Navigation via Deep Reinforcement Learning and Evolutionary Hybrid Design
Swarm robotics presents a robust and cost-effective paradigm for advanced automation in complex, dynamic environments, such as those encountered in search and rescue or environmental monitoring.Symmetry and AI-assisted discovery of magic-state factories
Magic-state distillation is a major resource cost in fault-tolerant quantum computing.BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation.On Learning Optimal Corners in Orthogonal Partially Observable Cooperative Guard Art Galleries
The CADENCE algorithm solves the Partially Observable Cooperative Guard Art Gallery Problem (POCGAGP) with formal coverage and connectivity guarantees, but leaves unspecified which valid corner each…Recursive Video In-Context Learning for Agentic Robot
LLM agents that orchestrate frozen vision-language-action (VLA) policies improve across episodes through text memory, which records what the agent did but not how the task is done.When to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent Memory
Persistent agent memory is only as reliable as its retention decision: an assertion weakly supported by its source can be stored and later reused as established fact.SPEAR: Five Principles for Interactive Human-Agent Alignment
Recent AI alignment work often frames alignment as a pre-deployment optimization problem: collect human feedback, learn preferences or principles, finetune the model, and deploy an aligned system.The Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent Memory
Long-term-memory agents can retrieve relevant information that is inadmissible for the current request because it belongs to another principal, violates policy, or reflects an incompatible lifecycle…Auditable Claims about AI Agents
Organizations make claims about their AI agents: a person approves every external email, every action is logged, an evaluation shows the agent is safe to deploy.Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning
When multiple agents share a cost budget, a common Lagrange multiplier can enforce the aggregate constraint but does not determine how its penalty should be allocated across agents.