Salvato in:
Dettagli Bibliografici
Autori principali: Xia, Defei, Pi, Bingfeng, Zhang, Shenbin, Hua, Song, Wei, Yunfei, Zuo, Lei
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.01857
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910001601183744
author Xia, Defei
Pi, Bingfeng
Zhang, Shenbin
Hua, Song
Wei, Yunfei
Zuo, Lei
author_facet Xia, Defei
Pi, Bingfeng
Zhang, Shenbin
Hua, Song
Wei, Yunfei
Zuo, Lei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01857
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios
Xia, Defei
Pi, Bingfeng
Zhang, Shenbin
Hua, Song
Wei, Yunfei
Zuo, Lei
Artificial Intelligence
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.
title Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios
topic Artificial Intelligence
url https://arxiv.org/abs/2601.01857