A multi-agent pipeline that reads a PDE problem description in plain text and writes, debugs, and validates a classical numerical solver end-to-end. Generates spectral and finite-dβ¦
Evaluates recommender systems via agent-RS interactions.
Introduces long-running multi-agent systems that self-evolve via shared persistent memory, asynchronous execution, and heartbeat-based interventions; 3β10Γ higher improvement ratesβ¦
Investigates dynamically rewiring agent-to-agent connections at each reasoning round via semantic matching instead of fixed communication topologies.
Explores automated game balancing by combining multi-agent LLM self-play with Bayesian optimization on a civ-style game.
Examines how conformal prediction can filter noisy inter-agent messages to improve multi-robot coordination.
Introduces a 110+ task benchmark to evaluate how well multi-agent LLM systems handle buyer-seller negotiation through natural language.
Analyzes social network formation among 70K+ autonomous LLM agents on Chirper.ai to study emergent group behavior and bias.
Proposes breaking large tasks into subtask trees that run in parallel across multiple agents to handle long-horizon workflows without exceeding context windows.
Proposes a deterministic multi-agent orchestrator where multiple LLMs analyze a problem independently and a merge agent selects the best answer without any training.
Simulates end-to-end hospital administrative workflows with multi-agent LLMs and FHIR integration to test LLM-driven automation in healthcare settings.
Proposes a multi-agent system for autonomous software engineering that assigns specialized agents to roles like coordination, research, implementation, and review.
Examines whether self-organizing LLM agent teams can match or beat their best member's performance across collaborative benchmarks.
Explores using LLM-driven genetic programming to automatically discover behavioral norms for multi-agent coordination in a survival-pressure grid-world simulation.
Proposes per-action process rewards from AI feedback to improve credit assignment and sample efficiency when finetuning multi-agent LLM systems.
Proposes a framework for safely growing multi-agent pools by generating familiarization tasks and building routing memory, with a guaranteed non-decreasing performance across onboaβ¦
Proposes a task-adaptive multi-agent framework that routes control to the most suitable LLM at each decision step using semantic matching against each model's success history.
Explores using a pool of different LLM agents within MCTS planning to increase rollout diversity and improve multi-step reasoning.
Proposes a recommendation framework that uses historical calling trees to select the best agents or agent teams for each subtask in multi-agent orchestration.
Investigates actor-critic reinforcement learning methods for training decentralized LLM agent collaboration across writing, coding, and game-playing tasks.
Proposes a role-structured multi-agent courtroom debate framework with defined agent roles, interaction protocols, and private reasoning strategies for auditable high-stakes decisiβ¦
Introduces a reasoning framework that builds peer reliability profiles from interaction history so agents in multi-agent systems learn which peers to trust when uncertain.
Explores structured multi-agent debate with three role-based agents and adaptive confidence gating to improve small language model code generation.
Proposes a lightweight router for dynamic model selection in graph-based multi-agent systems that combines semantic embeddings with structural meta-features and self-optimizes throβ¦
Develops a theory for predicting when budgeted multi-agent LLM systems improve, saturate, or collapse based on context windows, communication fidelity, and shared-error correlationβ¦
Proposes a meta-debate framework that dynamically assigns roles in multi-agent systems by matching model capabilities to positions through proposal and peer review stages.
Introduces orchestrated decentralized peer-to-peer LLM collaboration that uses contextual bandits to learn optimal matchmaking between heterogeneous agents via secure distillation.
Explores a runtime Mixture-of-Models architecture with a dynamic expertise broker and quadratic voting consensus that enables small model ensembles to match frontier performance.
Formalizes through operator theory why multi-agent LLM systems access invariant solutions that a single agent applying all constraints simultaneously cannot reach.
Proposes a training-time framework that formulates multi-agent orchestration as function-calling reinforcement learning with holistic system-level reasoning and introduces MASBENCHβ¦
Proposes a bi-level optimization framework for multi-agent companions that aligns individual personas via RLAIF and optimizes collaborative dialogue through group-level meta-policyβ¦
Explores a team-of-rivals multi-agent architecture with specialized roles and a remote code executor that separates reasoning from data execution to maintain clean context windows.
Formalizes a unified architectural framework for orchestrated multi-agent systems integrating MCP for tool access and Agent2Agent protocol for peer coordination, delegation, and poβ¦
Proposes Multi-Agent Reward Optimization, a method that decomposes multi-agent social interaction outcomes into per-behavior learning signals to improve LLM reasoning through simulβ¦
Introduces an LSTM-inspired multi-agent architecture with worker, filter, judge, and manager agents that emulate gated memory mechanisms to control information flow for long-contexβ¦
Examines whether query-level workflow generation is always necessary in multi-agent systems and proposes a low-cost task-level framework that uses self-prediction with few-shot calβ¦
Proposes a latency-aware multi-agent orchestration framework that explicitly optimizes the critical execution path under parallel execution to reduce end-to-end latency while maintβ¦
Proposes a one-shot topology generation framework with diverse interaction modes that enables decentralized agents to autonomously construct heterogeneous communication topologies β¦
Replaces predefined multi-agent workflows with a dynamic information-flow orchestrator that coordinates agents through natural-language A2A communication.
Reviews LLM-based multi-agent systems across the software development lifecycle, covering frameworks, communication protocols, and orchestration challenges from requirements to debβ¦
Explores injecting structured textual experience into multi-agent deliberation at test time to improve reasoning accuracy without any model tuning.
Argues that LLMs can replace hand-crafted numerical reward functions with language-based objective specifications for multi-agent coordination, drawing on EUREKA and RLVR as evidenβ¦
Analyzes over 42K commits and 4.7K resolved issues across eight leading multi-agent AI systems (LangChain, CrewAI, AutoGen, etc.) to study development patterns, maintenance practicβ¦
Proposes a hierarchical multi-agent framework that decouples high-level coordination from subtask execution with active task-level memory control and reinforcement-learning-driven β¦
Proposes a constrained temporal hierarchical architecture for multi-agent LLM systems that projects inter-layer communication onto structured manifolds with typed message contractsβ¦
Introduces dynamic path generation for multi-agent debate that allocates diverse solution paths to agents, shifts focus to step-by-step logic critique, and uses a trigger-based verβ¦
Investigates how diversity-aware initialization and confidence-modulated updates improve multi-agent debate, connecting findings from human deliberation research to LLM-based debatβ¦
Proposes a multi-agent framework with confidence-aware routing that dynamically selects agent roles and model scales across heterogeneous LLMs based on task complexity.
Analyzes role-based authority bias in multi-agent evaluation frameworks using French and Raven's power-based theory across legitimate, referent, and expert power types.
Investigates when a single agent with a skill library can replace multi-agent systems, studying scaling limits and phase transitions in skill selection as libraries grow.
Proposes a two-stage framework for enhancing multi-agent system resilience through RL-based topology generation and topology-aware prompt optimization under perturbations.
Proposes an adaptive reasoning router for multi-agent systems that generates natural-language reasoning chains before predicting candidate agents, with a collaborative execution piβ¦
Investigates covert communication in LLM multi-agent systems through game-theoretic analysis of implicit coordination signals across different communication regimes.
Proposes a Bayesian, cost-aware multi-LLM orchestration framework that treats LLMs as approximate likelihood models and aggregates across diverse models for sequential decision-makβ¦
Turns natural-language optimization problems into working solver code with a four-agent pipeline (Formulator, Planner, Coder, Critic) and UCB bandit scheduling over candidate formuβ¦
Despite enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains on popular benchmarks are often minimal. This gap highlights a critical need for a principled understaβ¦
In this paper, a mathematical model is developed to describe the evolution of the concentration of compounds through a gas chromatography column. The model couples mass balances anβ¦
Large Language Models (LLMs) have demonstrated near-human performance in summarization tasks based on traditional metrics such as ROUGE and BERTScore. However, these metrics do notβ¦
In this manuscript, we study a special class of correspondences on $\mathbb{P}^{1} \times \mathbb{P}^{1}$ given by a polynomial relation, say $P(z, w)$. We focus on what we call reβ¦