Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation. When computation is normalized, single-agent systems (SAS) can match or outperform MAS, yet the theoretical basis and evaluation methodology behind this comparison remain unclear. We present an information-theoretic argument, grounded in the Data Processing Inequality, suggesting that under a fixed reasoning-token budget and with perfect context utilization, single-agent systems are more information-efficient. This perspective further predicts that multi-agent systems become competitive when a single agent's effective context utilization is degraded, or when more compute is expended. We test these predictions in a controlled empirical study across three model families (Qwen3, DeepSeek-R1-Distill-Llama, and Gemini 2.5), comparing SAS with multiple MAS architectures under matched budgets. We find that SAS consistently match or outperform MAS on multi-hop reasoning tasks when reasoning tokens are held constant. Beyond aggregate performance, we conduct a detailed diagnostic analysis of system behavior and evaluation methodology. We identify significant artifacts in API-based budget control (particularly in Gemini 2.5) and in standard benchmarks, both of which can inflate apparent gains from MAS. Overall, our results suggest that, for multi-hop reasoning tasks, many reported advantages of multi-agent systems are better explained by unaccounted computation and context effects rather than inherent architectural benefits, and highlight the importance of understanding and explicitly controlling the trade-offs between compute, context, and coordination in agentic systems.
AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering
Computer Science, Fudan University(复旦大学计算机科学系);Institute of Modern Languages and Linguistics, Fudan University(复旦大学现代语言与语言学研究院);Shanghai Innovation Institute(上海创新研究院);Soochow University(苏州大学)
Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs
The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));The Hong Kong University of Science and Technology(香港科学与技术大学);Nanyang Technological University(南洋理工大学);Singapore Institute of Manufacturing Technology, A*STAR(新加坡制造技术研究所,A*STAR)
Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning
University of Science and Technology of China(中国科学技术大学);cmss.chinamobile.com(中移(苏州)软件技术有限公司);Lin Gang Laboratory(林冈实验室);ShanghaiTech University(上海科技大学)
ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection
National Key Laboratory for Novel Software Technology, Nanjing University, Jiangsu, China(新型软件技术国家重点实验室,南京大学,江苏,中国);Shanghai Artificial Intelligence Laboratory, Shanghai, China(上海人工智能实验室,上海,中国);Department of Linguistics and Translation, City University of Hong Kong, Hong Kong, China(语言学与翻译系,香港城市大学,香港,中国);School of Mathematical Sciences, Dalian University of Technology, Liaoning, China(数学科学学院,大连理工大学,辽宁,中国)
Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院);Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系);Ant Group(蚂蚁集团)
Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
Harbin Institute of Technology(哈尔滨工业大学);Beijing University of Posts and Telecommunications(北京邮电大学);Joint Laboratory of HIT and iFLYTEK(哈工大与科大讯飞联合实验室);University of Science and Technology of China(中国科学技术大学);Pengcheng Laboratory(鹏城实验室)
Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism
College of Computer Science and Technology, National University of Defense Technology(计算机科学与技术学院,国防科技大学);College of Intelligence Science and Technology, National University of Defense Technology(智能科学与技术学院,国防科技大学)
THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models
School of Artificial intelligence, JiLin University(吉林大学人工智能学院);Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, JiLin University(吉林大学知识驱动人机智能工程研究中心);International Center of Future Science, JiLin University(吉林大学未来科学国际中心)
Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion
School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院);National University of Singapore(新加坡国立大学);Inner Mongolia Research Institute, Shanghai Jiao Tong University(上海交通大学内蒙古研究院)
H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking
Duke University(杜克大学);Accenture(埃森哲);Accenture Security(埃森哲安全)
DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
Korea University(高丽大学);dot(42dot);Konkuk University(建国大学);Yonsei University(延世大学);Soongsil University(崇实大学);Kumoh National Institute of Technology(金乌国立技术学院)
In-Context Learning on a Budget: A Case Study in Token Classification
School of Computer Science and Engineering, The Hebrew University of Jerusalem(耶路撒冷希伯来大学计算机科学与工程学院);School of Computing and Information Systems, University of Melbourne(墨尔本大学计算与信息系统学院);Microsoft Corporation(微软公司)
PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning
Center for Healthcare Organization and Implementation Research, VA Bedford Health Care(VA Bedford Health Care 医疗组织与实施研究中心);Manning College of Information and Computer Sciences, University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校信息与计算机科学学院);Miner School of Computer and Information Sciences, University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校 Miner 信息与计算机科学学院)
School of Computer Science, Beijing University of Posts and Telecommunications(北京邮电大学计算机学院);Tsinghua University(清华大学);Beijing National Research Center for Information Science and Technology (BNRist)(北京信息科学与技术国家研究中心);Kuaishou Technology(快手科技);Shanghai Jiao Tong University(上海交通大学)