SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models

arXiv cs.AI Papers

Summary

SMAC-Talk is a new benchmark that extends the StarCraft Multi-Agent Challenge to evaluate LLM-based agents in cooperative multi-agent environments with natural language communication. It includes scenarios with deceptive communicators and benchmarks agents using models from the Qwen3.5 family to study how reasoning, memory, and scale affect coordination.

arXiv:2606.04202v1 Announce Type: new Abstract: As LLMs become more widely deployed, they are increasingly expected to work alongside other AI agents rather than operating in isolation. Effective coordination in these settings requires agents to communicate, share information and make decisions under uncertainty. We introduce SMAC-Talk, a natural language extension of the StarCraft Multi-Agent Challenge for evaluating LLM-based agents in cooperative multi-agent environments. The environment has several key features such as decentralized control, partial observability and long-horizon decision making. SMAC-Talk includes a natural language communication channel which is used to probe agent coordination and trust. We use this communication channel to construct different evaluation scenarios, including settings with an embedded deceptive communicator that tries to disrupt and deceive allies through communication alone. We provide three agents for benchmarking using 4 models from the Qwen3.5 family and study how reasoning structure, memory and model scale affect coordination between agents. We release SMAC-Talk as an open benchmark to support the research community in developing and evaluating LLM agents in cooperative multi-agent settings.
Original Article
View Cached Full Text

Cached at: 06/05/26, 02:05 AM

# SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models
Source: [https://arxiv.org/abs/2606.04202](https://arxiv.org/abs/2606.04202)
[View PDF](https://arxiv.org/pdf/2606.04202)[HTML \(experimental\)](https://arxiv.org/html/2606.04202v1)

> Abstract:As LLMs become more widely deployed, they are increasingly expected to work alongside other AI agents rather than operating in isolation\. Effective coordination in these settings requires agents to communicate, share information and make decisions under uncertainty\. We introduce SMAC\-Talk, a natural language extension of the StarCraft Multi\-Agent Challenge for evaluating LLM\-based agents in cooperative multi\-agent environments\. The environment has several key features such as decentralized control, partial observability and long\-horizon decision making\. SMAC\-Talk includes a natural language communication channel which is used to probe agent coordination and trust\. We use this communication channel to construct different evaluation scenarios, including settings with an embedded deceptive communicator that tries to disrupt and deceive allies through communication alone\. We provide three agents for benchmarking using 4 models from the Qwen3\.5 family and study how reasoning structure, memory and model scale affect coordination between agents\. We release SMAC\-Talk as an open benchmark to support the research community in developing and evaluating LLM agents in cooperative multi\-agent settings\.

## Submission history

From: Joel Sol \[[view email](https://arxiv.org/show-email/d54f9fd3/2606.04202)\] **\[v1\]**Tue, 2 Jun 2026 20:40:04 UTC \(866 KB\)

Similar Articles

Exploring Collaboration between a language and a non-language agent

Hugging Face Daily Papers

The paper introduces LLAMIA-Bench, a benchmark for collaborative chess tasks between language models and non-language agents, and proposes latent state internalization to outperform text-based verbalization, with a 14B model matching or exceeding frontier models like GPT-5.1.

TMAS: Scaling Test-Time Compute via Multi-Agent Synergy

Hugging Face Daily Papers

TMAS introduces a multi-agent framework that enhances large language model reasoning by scaling test-time compute through structured collaboration and hierarchical memory systems. The approach uses specialized agents, cross-trajectory information flow, and hybrid reward reinforcement learning to improve iterative scaling and stability on challenging reasoning benchmarks.

Decentralized Multi-Agent Systems with Shared Context

Hugging Face Daily Papers

This paper introduces Decentralized Language Models (DeLM), a framework for multi-agent systems that uses parallel agents with a shared verified context to improve test-time scaling and reduce costs, achieving state-of-the-art results on SWE-bench Verified and LongBench-v2.