Changjiang Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Changjiang Zhou has a total of 11 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
6 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
6 shared publications - Xueqi Cheng
Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China
5 shared publications - Maarten de Rijke
University of Amsterdam, Amsterdam, Netherlands
4 shared publications - Jiangui Chen
ICT, CAS & University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Yixing Fan
State Key Laboratory of AI Safety; Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, China
2 shared publications
Latest Publications
- 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.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1983-1992
Déjà Vu of Strange Stickers! Enhancing Out-of-Distribution Robustness in Sticker Retrieval via Cross-Modal Intent Alignment
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1983-1992
Open AccessDéjà Vu of Strange Stickers! Enhancing Out-of-Distribution Robustness in Sticker Retrieval via Cross-Modal Intent Alignment
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2004-2013
LongRanker: Efficient One-Pass Document Reranking with Long-Context Large Language Models
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2004-2013
Open AccessLongRanker: Efficient One-Pass Document Reranking with Long-Context Large Language Models
- Open Access
- 25 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks
Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents from trustworthy corpora, e.g., Wikipedia, to produce specific answers. Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance. However, most research on KILTs, including CorpusBrain, has predominantly focused on a static document collection, overlooking the dynamic nature of real-world scenarios, where new documents are continuously being incorporated into the source corpus. To address this gap, it is crucial to explore the capability of retrieval models to effectively handle the dynamic retrieval scenario inherent in KILTs. In this work, we first introduce the continual document learning (CDL) task for KILTs and build a novel benchmark dataset named KILT++ based on the original KILT dataset for evaluation. Then, we conduct a comprehensive study of the use of pre-trained CorpusBrain on KILT++. Unlike the promising results in the stationary scenario, CorpusBrain is prone to catastrophic forgetting in the dynamic scenario, hence hampering retrieval performance. To alleviate this issue, we propose CorpusBrain++, a continual generative pre-training framework that enhances the original model along two key dimensions: (i) We employ a backbone-adapter architecture: the dynamic adapter is learned for each downstream KILT task via task-specific pre-training objectives; the backbone parameters that are task-shared are kept unchanged to offer foundational retrieval capacity. (ii) We use an experience replay strategy based on exemplar documents that are similar to new documents, to prevent catastrophic forgetting of old documents. Empirical results demonstrate the effectiveness and efficiency of CorpusBrain++ in comparison to both traditional and generative information retrieval methods.
- 25 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
Open AccessCorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks
Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents from trustworthy corpora, e.g., Wikipedia, to produce specific answers. Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance. However, most research on KILTs, including CorpusBrain, has predominantly focused on a static document collection, overlooking the dynamic nature of real-world scenarios, where new documents are continuously being incorporated into the source corpus. To address this gap, it is crucial to explore the capability of retrieval models to effectively handle the dynamic retrieval scenario inherent in KILTs. In this work, we first introduce the continual document learning (CDL) task for KILTs and build a novel benchmark dataset named KILT++ based on the original KILT dataset for evaluation. Then, we conduct a comprehensive study of the use of pre-trained CorpusBrain on KILT++. Unlike the promising results in the stationary scenario, CorpusBrain is prone to catastrophic forgetting in the dynamic scenario, hence hampering retrieval performance. To alleviate this issue, we propose CorpusBrain++, a continual generative pre-training framework that enhances the original model along two key dimensions: (i) We employ a backbone-adapter architecture: the dynamic adapter is learned for each downstream KILT task via task-specific pre-training objectives; the backbone parameters that are task-shared are kept unchanged to offer foundational retrieval capacity. (ii) We use an experience replay strategy based on exemplar documents that are similar to new documents, to prevent catastrophic forgetting of old documents. Empirical results demonstrate the effectiveness and efficiency of CorpusBrain++ in comparison to both traditional and generative information retrieval methods.
- 4 April 2025
- Published by Springer Nature
- p. 407-423
On the Robustness of Generative Information Retrieval Models: An Out-of-Distribution Perspective
- 4 April 2025
- Published by Springer Nature
- p. 407-423
On the Robustness of Generative Information Retrieval Models: An Out-of-Distribution Perspective
- Open Access
CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks
Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents from trustworthy corpora, e.g., Wikipedia, to produce specific answers. Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance. However, most existing research on KILTs, including CorpusBrain, has predominantly focused on a static document collection, overlooking the dynamic nature of real-world scenarios, where new documents are continuously being incorporated into the source corpus. To address this gap, it is crucial to explore the capability of retrieval models to effectively handle the dynamic retrieval scenario inherent in KILTs. In this work, we first introduce the continual document learning (CDL) task for KILTs and build a novel benchmark dataset named KILT++ based on the original KILT dataset for evaluation. Then, we conduct a comprehensive study over the use of pre-trained CorpusBrain on KILT++. Unlike the promising results in the stationary scenario, CorpusBrain is prone to catastrophic forgetting in the dynamic scenario, hence hampering the retrieval performance. To alleviate this issue, we propose CorpusBrain++, a continual generative pre-training framework. Empirical results demonstrate the significant effectiveness and remarkable efficiency of CorpusBrain++ in comparison to both traditional and generative IR methods.
Open AccessCorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks
Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents from trustworthy corpora, e.g., Wikipedia, to produce specific answers. Very recently, a pre-trained generative retrieval model for KILTs, named CorpusBrain, was proposed and reached new state-of-the-art retrieval performance. However, most existing research on KILTs, including CorpusBrain, has predominantly focused on a static document collection, overlooking the dynamic nature of real-world scenarios, where new documents are continuously being incorporated into the source corpus. To address this gap, it is crucial to explore the capability of retrieval models to effectively handle the dynamic retrieval scenario inherent in KILTs. In this work, we first introduce the continual document learning (CDL) task for KILTs and build a novel benchmark dataset named KILT++ based on the original KILT dataset for evaluation. Then, we conduct a comprehensive study over the use of pre-trained CorpusBrain on KILT++. Unlike the promising results in the stationary scenario, CorpusBrain is prone to catastrophic forgetting in the dynamic scenario, hence hampering the retrieval performance. To alleviate this issue, we propose CorpusBrain++, a continual generative pre-training framework. Empirical results demonstrate the significant effectiveness and remarkable efficiency of CorpusBrain++ in comparison to both traditional and generative IR methods.