This study provides the first large-scale empirical comparison of agentic frameworks for reasoning-intensive software engineering tasks and shows that framework selection should prioritize orchestration quality, especially memory control, failure handling, and cost management.
Abstract
Recent advances in agentic frameworks have enabled AI agents to perform complex reasoning and decision-making. However, evidence comparing their reasoning performance, efficiency, and practical suitability remains limited. To address this gap, we empirically evaluate 22 widely used agentic frameworks across three reasoning benchmarks: BBH, GSM8K, and ARC. The frameworks were selected from 1,200 GitHub repositories collected between January 2023 and July 2025 and organized into a taxonomy based on architectural design. We evaluated them under a unified setting, measuring reasoning accuracy, execution time, computational cost, and cross-benchmark consistency. Our results show that 19 of the 22 frameworks completed all three benchmarks. Among these, 12 showed stable performance, with mean accuracy of 74.6-75.9%, execution time of 4-6 seconds per task, and cost of 0.14-0.18 cents per task. Poorer results were mainly caused by orchestration problems rather than reasoning limits. For example, Camel failed to complete BBH after 11 days because of uncontrolled context growth, while Upsonic consumed USD 1,434 in one day because repeated extraction failures triggered costly retries. AutoGen and Mastra also exhausted API quotas through iterative interactions that increased prompt length without improving results. We also found a sharp drop in mathematical reasoning. Mean accuracy on GSM8K was 44.35%, compared with 89.80% on BBH and 89.56% on ARC. Overall, this study provides the first large-scale empirical comparison of agentic frameworks for reasoning-intensive software engineering tasks and shows that framework selection should prioritize orchestration quality, especially memory control, failure handling, and cost management.
Through applied case studies in pharmaceutical discovery and financial systems, common design patterns that make agentic systems successful are analyzed, and practical mitigation strategies for failure modes are discussed, such as verification pipelines, fallback mechanisms, and human-in-the-loop supervision.
Grace Hui Yang, P. Venkit, Hooman Sedghamiz et al.· Proceedings of the 32nd ACM...· 0 citations
A unified, taxonomy-driven, and deployment-oriented survey of agentic AI systems, synthesizing recent advances through a modular reference architecture and a four-dimensional taxonomy that characterizes agents along the axes of autonomy, tool use, collaboration, and safety–governance is presented.
Sparsh Bajoria, Shreyanshu Ranjan, Adhitya M et al.· Cognitive Computation· 0 citations
This position paper outlines a common abstraction layer that can substantially lower the effort for designing agents with constrained creativity, and demonstrates early promise of this paradigm for two SysOps use cases: Root Cause Analysis and Network Configuration Generation.
†. SayanSinha, Vipul Harsh, Yajie Zhou et al.· 0 citations
Analysis shows that BRANCH's advantage arises not only from exploring multiple reasoning paths, but also from recovering from truncation: its gains strongly correlate with the baseline rate of empty, budget-exhausted outputs, weakening the hypothesis that different problems require routing among test-time reasoning operators.
Sheng Zhang, Xiao-Min Wu, Xiyang Wu et al.· 0 citations
ClawTrack is presented, a dual-assessment benchmark that simultaneously measures what an agent achieves (Task Score) and how it achieves it (Process Score) and finds that process scores effectively attribute success and failure to specific reasoning dimensions, filtering lucky passes invisible to outcome-only evaluation.
Xingjian Wu, Xuhan Zhu, Xing-Chen Liu et al.· arXiv.org· 0 citations
Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and complex task execution. However, current approaches to manually designing and optimizing agentic systems heavily rely on manual effort, limiting their adaptability and scalability. Recent work has explored the automated optimization of workflow designs. However, these approaches often overlook the crucial role of model capabilities and focus on single performance metrics, failing to address real-world deployment constraints. In this paper, we present AgentFactory, a framework that jointly optimizes both foundation models and workflow structures in agentic systems while considering multiple objectives including performance, cost, and efficiency. AgentFactory leverages advanced LLMs as optimizers to navigate the vast search space of possible configurations, employing a three-stage optimization pipeline to automatically discover effective combinations of fine-tuned models and optimized workflows. Through an iterative optimization process, our framework systematically explores and evaluates different agentic system designs, adapting to task-specific requirements while maintaining operational efficiency. We evaluate AgentFactory across eight benchmarks spanning five domains, including general reasoning, coding, mathematics, medicine, and finance. Our experiments demonstrate that AgentFactory consistently outperforms both manually designed methods and existing automated approaches, achieving an average improvement of 9.1% across all benchmarks, with particularly significant gains in domain-specific tasks (19.6% on MedQA and 18.7% on FinEval). These results establish AgentFactory as a promising approach for developing more capable and efficient agentic systems through automated optimization.
En-Ci Zhang, Hao-Fen Wang, Yuesheng Zhu et al.· Pacific Rim International Co...· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comJul 30, 2026
Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve. The post Echoverse: Deep, evolving environments for computer-use agents appeared first on Microsoft Research.
Computer scientist Phillip Isola cuts through the hype to explain how AI agents work and what the future might hold for this rapidly advancing technology.
