Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios

2026-01-05

arXiv.org

AI Summary

This work addresses the limitations of large language model–driven autonomous agents in real-world scenarios, particularly their insufficient accuracy in contextual understanding, tool invocation, and response generation. To overcome these challenges, we propose an end-to-end agent framework that integrates adaptive prompt generation, context-aware tool orchestration, and a dynamic hierarchical memory mechanism combining conversational, task-specific, and externally summarized knowledge. By leveraging the Model Context Protocol (MCP) for tool integration, semantic retrieval, and dynamic summary compression—augmented with an execution feedback loop—the framework significantly refines reasoning and tool utilization processes. Experimental results demonstrate that deployment on the Jenius platform yields a 20% improvement in task accuracy while simultaneously reducing token consumption, response latency, and tool invocation failure rates.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

As agent systems powered by large language models (LLMs) advance, improving performance in context understanding, tool usage, and long-horizon execution has become critical. However, existing agent frameworks and benchmarks provide limited visibility into execution-level behavior, making failures in tool invocation, state tracking, and context management difficult to diagnose. This paper presents Jenius-Agent, a system-level agent framework grounded in real-world deployment experience. It integrates adaptive prompt generation, context-aware tool orchestration, and layered memory mechanism to stabilize execution and improve robustness in long-horizon, tool-augmented tasks. Beyond system design, we introduce an evaluation methodology that jointly measures procedural fidelity, semantic correctness, and efficiency. This framework makes agent behavior observable as a structured execution process and enables systematic analysis of failure modes not captured by output-only metrics. Experiments on Jenius-bench show substantial improvements in task completion rate, with up to a 35 percent relative gain over the base agent, along with reduced token consumption, response latency, and tool invocation failures. The framework is already deployed in Jenius ({https://www.jenius.cn}), providing a lightweight and scalable solution for robust, protocol-compatible autonomous agents.

Problem

• LLM-based agents
• task accuracy
• tool usage
• context understanding
• autonomous agents

Innovation

• adaptive prompting
• context-aware tool orchestration
• layered memory mechanism
• LLM-based agent
• Model Context Protocol