REVIEW 12 cited by
MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition. In this paper, we introduce MultiAgentBench, a comprehensive benchmark designed to evaluate LLM-based multi-agent systems across diverse, interactive scenarios. Our framework measures not only task completion but also the quality of collaboration and competition using novel, milestone-based key performance indicators. Moreover, we evaluate various coordination protocols (including star, chain, tree, and graph topologies) and innovative strategies such as group discussion and cognitive planning. Notably, gpt-4o-mini reaches the average highest task score, graph structure performs the best among coordination protocols in the research scenario, and cognitive planning improves milestone achievement rates by 3%. Code and datasets are public available at https://github.com/MultiagentBench/MARBLE.
Forward citations
Cited by 12 Pith papers
-
SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents
SciVisAgentBench provides 108 expert-crafted tasks and a mixed LLM-plus-deterministic evaluation pipeline for benchmarking AI agents that perform scientific visualization workflows.
-
Choose Your Agent: Tradeoffs in Adopting AI Advisors, Coaches, and Delegates in Multi-Party Negotiation
Users prefer an AI Advisor but gain most with a Delegate, because human editing filters out the AI's best proposals.
-
UserBench: An Interactive Gym Environment for User-Centric Agents
A new multi-turn agent benchmark shows that current LLMs elicit fewer than 30% of user preferences and reach full intent alignment only about 20% of the time.
-
Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review
A survey proposing adaptability as a three-part taxonomy (learning, policy, scenario-driven) for organizing and evaluating MARL under changing conditions.
-
MAEBE: Multi-Agent Emergent Behavior Framework
Multi-agent LLM ensembles show different and less predictable moral preferences than single models, with convergence driven by peer pressure, according to a new evaluation framework.
-
Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details
For Other-Play in Yokai, agents trained with different implementation details coordinate across implementations about as well as across seeds, supporting inter-seed cross-play as a proxy for cross-implementation evaluation.
-
The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards
MAS-HQ defines a resource-aware Q-Score and shows that the system with the highest raw factuality is often not the winner once normalized cost is subtracted.
-
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities
AgentCompass is a modular evaluation infrastructure that decouples benchmark, harness, and environment for LLM agents, and its experiments show model scores vary substantially with the harness used.
-
OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence
OpenHospital is an interactive physician-patient multi-agent arena that improves clinical metrics via ground-truth reflection and reports cooperative behaviors as evidence of evolving LLM collective intelligence.
-
Agent Identity Evals: Measuring Agentic Identity
Introduces Agent Identity Evals (AIE), five similarity-based metrics for LMA identity stability, with pilot experiments showing identifiability always at zero and no statistical support.
-
Know the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System Design
A heuristic framework that decomposes known algorithms into typed LLM-agent subtasks lifts small-model accuracy on knapsack and assignment problems from near-zero to high levels after fixing one bottleneck agent.
-
Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey
A survey that classifies AI agent evaluation benchmarks along environment and capability axes, and proposes five traits that distinguish agents from chatbots.
Discussion (0). Continue with ORCID to comment.