Yingchen Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yingchen Zhang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Jiafeng Guo
School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Ruqing Zhang
State Key Laboratory of AI Safety, The Institute of Computing Technology,CAS, Beijing, Beijing, China and University of Chinese Academy of Sciences, Beijing, Beijing, China
2 shared publications - Changjiang Zhou
State Key Laboratory of AI Safety; Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, China
1 shared publication - Furong Li
Huawei Technologies Co., Ltd, China
1 shared publication - Jiayu Yao
State Key Laboratory of AI Safety; Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, China
1 shared publication - Shenghua Liu
State Key Laboratory of AI Safety; Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, China
1 shared publication
Latest Publications
- Open Access
- 15 October 2026
- Published by MDPI AG in Preprints.org
From Trajectories to Experience: A Survey of Experience-Driven LLM Agents
Large language model (LLM) agents can plan, use tools, and recover from errors within a task, yet many carry little from one task to the next and repeat mistakes they have already resolved. The root cause is a lack of experience accumulation: trajectories record what failed and how the agent recovered, but this information is seldom turned into guidance for later tasks. Research on this capability spans reflection, agent memory, workflow learning, and skill acquisition, but these lines describe similar content in different terms and lack a common account of experience itself, leaving basic questions open: what counts as experience, how it should be accumulated, used, and revised, and how to tell whether it improves later behavior. This survey addresses these questions with a unified framework. We define agent experience as action-guiding information grounded in task trajectories and retained to guide later episodes where it applies, whether as a trajectory precedent, a semantic lesson, or a reusable procedure. We focus on explicitly accessible experience, including its use as a training signal for internalization into model parameters. We describe each unit of experience by its guidance, applicability conditions, execution evidence, and reliability evaluation, so that memory entries, workflows, and skills become directly comparable, and follow experience through four lifecycle functions---formation, organization, utilization, and maintenance---that determine how it is accumulated, used, and revised. To judge reported gains, we distinguish three improvement claims---fixed experience reuse, feedback-driven sustained improvement, and improvement of the learning mechanism---by the evidence each requires. Current studies most clearly support fixed experience reuse, chiefly on tasks with tests or reference answers; evidence for the other two claims remains partial. Our analysis yields recommendations for seven application settings and a central design principle: keep guidance connected to its applicability conditions and to the evidence that supports or challenges it. Finally, we outline eight open problems, from learning with human expert records to testing whether gains accumulate, toward agents whose improvement is cumulative, transferable, and correctable.
- 15 October 2026
- Published by MDPI AG in Preprints.org
Open AccessFrom Trajectories to Experience: A Survey of Experience-Driven LLM Agents
Large language model (LLM) agents can plan, use tools, and recover from errors within a task, yet many carry little from one task to the next and repeat mistakes they have already resolved. The root cause is a lack of experience accumulation: trajectories record what failed and how the agent recovered, but this information is seldom turned into guidance for later tasks. Research on this capability spans reflection, agent memory, workflow learning, and skill acquisition, but these lines describe similar content in different terms and lack a common account of experience itself, leaving basic questions open: what counts as experience, how it should be accumulated, used, and revised, and how to tell whether it improves later behavior. This survey addresses these questions with a unified framework. We define agent experience as action-guiding information grounded in task trajectories and retained to guide later episodes where it applies, whether as a trajectory precedent, a semantic lesson, or a reusable procedure. We focus on explicitly accessible experience, including its use as a training signal for internalization into model parameters. We describe each unit of experience by its guidance, applicability conditions, execution evidence, and reliability evaluation, so that memory entries, workflows, and skills become directly comparable, and follow experience through four lifecycle functions---formation, organization, utilization, and maintenance---that determine how it is accumulated, used, and revised. To judge reported gains, we distinguish three improvement claims---fixed experience reuse, feedback-driven sustained improvement, and improvement of the learning mechanism---by the evidence each requires. Current studies most clearly support fixed experience reuse, chiefly on tasks with tests or reference answers; evidence for the other two claims remains partial. Our analysis yields recommendations for seven application settings and a central design principle: keep guidance connected to its applicability conditions and to the evidence that supports or challenges it. Finally, we outline eight open problems, from learning with human expert records to testing whether gains accumulate, toward agents whose improvement is cumulative, transferable, and correctable.
- Open Access
- 20 September 2026
- Published by MDPI AG in Preprints.org
Scaling Interactive Learning Resources for LLM Agents: A Survey of Environment and Task Synthesis
Large language model (LLM) agents can learn through interaction with external environments, obtain training signals and reusable experience from task execution. Scaling this form of learning requires a sufficient supply of interactive environments and tasks grounded in those environments, with explicit objectives and completion criteria. We refer to these complementary resources as interactive learning resources. This survey reviews their automated construction at scale and continuous adaptation through three interconnected themes: environment synthesis, task synthesis, and learning-driven evolution of both. For environment synthesis, we examine functional components, construction paradigms, and intrinsic quality assurance. For task synthesis, we review intent formation, grounding, completion verification, and task quality assurance. We then examine how a target agent's performance and learning progress inform assessments of resource suitability and guide adaptation to its evolving capabilities and learning needs across successive learning rounds. Finally, we discuss open challenges concerning the order of environment and task synthesis, the trade-off between intrinsic quality and learning utility, long-term resource evolution, and quality assurance at scale.
- 20 September 2026
- Published by MDPI AG in Preprints.org
Open AccessScaling Interactive Learning Resources for LLM Agents: A Survey of Environment and Task Synthesis
Large language model (LLM) agents can learn through interaction with external environments, obtain training signals and reusable experience from task execution. Scaling this form of learning requires a sufficient supply of interactive environments and tasks grounded in those environments, with explicit objectives and completion criteria. We refer to these complementary resources as interactive learning resources. This survey reviews their automated construction at scale and continuous adaptation through three interconnected themes: environment synthesis, task synthesis, and learning-driven evolution of both. For environment synthesis, we examine functional components, construction paradigms, and intrinsic quality assurance. For task synthesis, we review intent formation, grounding, completion verification, and task quality assurance. We then examine how a target agent's performance and learning progress inform assessments of resource suitability and guide adaptation to its evolving capabilities and learning needs across successive learning rounds. Finally, we discuss open challenges concerning the order of environment and task synthesis, the trade-off between intrinsic quality and learning utility, long-term resource evolution, and quality assurance at scale.