dorsal/arxiv
View SchemaLong-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments
| Authors | Qinglong Shi, Donghai Wang, Hantao Zhou, Jiguo Li, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He |
|---|---|
| Categories | |
| ArXiv ID | 2601.09382vv1 |
| URL | https://arxiv.org/abs/2601.09382 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Current large language model agents predominantly operate under a reactive paradigm, responding only to immediate user queries within short-term sessions. This limitation hinders their ability to maintain long-term user's intents and dynamically adapt to evolving external environments. In this paper, we propose a novel interaction paradigm for proactive Task-oriented Agents capable of bridging the gap between relatively static user's needs and a dynamic environment. We formalize proactivity through two key capabilities, (i) Intent-Conditioned Monitoring: The agent autonomously formulates trigger conditions based on dialog history; (ii) Event-Triggered Follow-up: The agent actively engages the user upon detecting useful environmental updates. We introduce a high-quality data synthesis pipeline to construct complex, multi-turn dialog data in a dynamic environment. Furthermore, we attempt to address the lack of evaluation criteria of task-oriented interaction in a dynamic environment by proposing a new benchmark, namely ChronosBench. We evaluated some leading close-source and open-source models at present and revealed their flaws in long-term task-oriented interaction. Furthermore, our fine-tuned model trained using synthetic data for supervised learning achieves a task completion rate of 85.19% for complex tasks including shifts in user intent, outperforming other models under test. And the result validated the effectiveness of our data-driven strategy.
{
"annotation_id": "c8c65e22-6749-472a-9ac5-928307c77de2",
"date_created": "2026-02-17T05:53:20.110000Z",
"date_modified": "2026-02-17T05:53:20.110000Z",
"file_hash": "1ac13da4178ab164cf1c127a32f1afb6dc03e85ff2fa5100da343973134d84b0",
"private": false,
"record": {
"abstract": "Current large language model agents predominantly operate under a reactive paradigm, responding only to immediate user queries within short-term sessions. This limitation hinders their ability to maintain long-term user\u0027s intents and dynamically adapt to evolving external environments. In this paper, we propose a novel interaction paradigm for proactive Task-oriented Agents capable of bridging the gap between relatively static user\u0027s needs and a dynamic environment. We formalize proactivity through two key capabilities, (i) Intent-Conditioned Monitoring: The agent autonomously formulates trigger conditions based on dialog history; (ii) Event-Triggered Follow-up: The agent actively engages the user upon detecting useful environmental updates. We introduce a high-quality data synthesis pipeline to construct complex, multi-turn dialog data in a dynamic environment. Furthermore, we attempt to address the lack of evaluation criteria of task-oriented interaction in a dynamic environment by proposing a new benchmark, namely ChronosBench. We evaluated some leading close-source and open-source models at present and revealed their flaws in long-term task-oriented interaction. Furthermore, our fine-tuned model trained using synthetic data for supervised learning achieves a task completion rate of 85.19% for complex tasks including shifts in user intent, outperforming other models under test. And the result validated the effectiveness of our data-driven strategy.",
"arxiv_id": "2601.09382",
"authors": [
"Qinglong Shi",
"Donghai Wang",
"Hantao Zhou",
"Jiguo Li",
"Jun Xu",
"Jiuchong Gao",
"Jinghua Hao",
"Renqing He"
],
"categories": [
"cs.AI",
"cs.CL"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments",
"url": "https://arxiv.org/abs/2601.09382",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "88df32ff-df98-4b1f-972e-16d49c87a6e6",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}