Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios
This work addresses the need for more robust and observable agent systems in real-world deployments, offering a scalable solution for autonomous agents, though it appears incremental as it builds on existing agent frameworks with new components.
The paper tackles the problem of limited visibility into execution-level behavior in agent systems, which makes failures in tool invocation and context management difficult to diagnose, by presenting Jenius-Agent, a system-level framework that improves task completion rates by up to 35% relative gain over base agents and reduces token consumption, latency, and tool invocation failures.
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.