From the 1 of 15 linked papers with an AI index.
15 papers
NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs
Jiarong Zhao, Zhikai Lei, Zhiheng Xi +5
The paper presents NexForge, a requirement‑first framework that automatically turns free‑form capability requirements into executable agent training tasks, scaling data generation…
Task-Differentiated Atomic Skill Expansion and Routing for Continual Learning Across Highly Heterogeneous Tasks
Jiacheng Wang, Xinjia He, Qi Ding +5
Continual learning (CL) is commonly studied under the assumption that sequential tasks are semantically related or structurally similar. However, in highly heterogeneous settings,…
Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents
Bo Mao, Jie Zhou, Yutao Yang +5
Lifelong learning is essential for Large Language Model (LLM) agents operating in dynamic, interactive environments. However, existing lifelong learning agents for long-horizon tas…
Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
Bihao Zhan, Jie Zhou, Junsong Li +9
Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. T…
PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor
Yutao Yang, Junsong Li, Qianjun Pan +7
Existing methods for AI psychological counselors predominantly rely on supervised fine-tuning using static dialogue datasets. However, this contrasts with human experts, who contin…
LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
Junsong Li, Jie Zhou, Bihao Zhan +7
Alignment plays a crucial role in Large Language Models (LLMs) in aligning with human preferences on a specific task/domain. Traditional alignment methods suffer from catastrophic…