This study demonstrates that instruction-tuned language model agents exhibit robust, group-contingent in-group bias, structurally mimicking human social biases, even when standard action logs fail to…

This paper investigates how individual agent biases amplify system-wide unfairness in multi-agent systems, demonstrating that uniform exposure to bias can elevate overall bias beyond the sum of indivi…

The paper proposes TCP-MCP, a co-evolution framework that jointly optimizes agent prompts and communication topologies to design highly efficient and effective multi-agent systems.

The paper introduces an outer-loop AI agent that autonomously redesigns LLM policy-synthesis pipelines for multi-agent social dilemmas, demonstrating that the optimal pipeline structure depends critic…

The paper introduces CyBiasBench, a comprehensive benchmark that quantifies the inherent, agent-specific bias in LLM agents' attack selection patterns in cybersecurity scenarios.

The paper introduces Mindgames, a comprehensive multi-game arena for evaluating LLM agents' sustained social and strategic reasoning, demonstrating that current evaluations are limited by structural s…

The paper decomposes LLM debate convergence into three mechanisms (instability, conformity, persuasion) and finds that much observed convergence is harmful social compliance rather than genuine reason…

The paper evaluates dynamic coordination strategy selection for enterprise multi-agent systems, finding that a calibrated default routing approach is effective, even if a deterministic winner-selectio…

The paper experimentally evaluates 12 multi-agent LLM collaboration topologies for software design, finding that structural adversarial prompting and cross-model review are the most effective approach…

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

The paper introduces PTCG-Bench, a new benchmark using the Pokémon TCG to evaluate LLM agents' strategic decision-making and ability to self-evolve, finding that sustained self-evolution remains chall…

The paper proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improveme…

The paper proposes using an LLM aggregator that analyzes complete reasoning traces, demonstrating that trace-level synthesis is superior to traditional consensus methods like majority voting for solvi…

CoopGuard is a novel stateful, multi-round defense framework using cooperative agents to significantly reduce the success rate of evolving adversarial attacks against Large Language Models.

The paper identifies 'memory-induced tool-drift,' a systematic vulnerability where personality biases stored in an LLM agent's memory silently corrupt tool-calling decisions, even when those biases ar…

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

This paper investigates if team-based interaction improves LLM performance on complex reasoning tasks (ChGK), finding that structured team strategies significantly boost accuracy by acting as error-fi…

This paper introduces a welfare-centric framework for designing institutional incentives, showing that optimizing for total social welfare often requires different incentive levels than those optimize…

This study provides a comprehensive benchmark of 10 frontier LLMs on 200 offensive cybersecurity tasks, finding that environment tooling and model selection are the primary performance drivers, with C…

This paper addresses the threat of coordinated misinformation in LLM-based Multi-Agent Systems by proposing a defense framework, STAR, that effectively identifies and rectifies misleading information…