Ke Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ke Zeng has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Guanglu Wan
Meituan
3 shared publications - Caixia Yuan
Beijing University of Posts and Telecommunications
2 shared publications - Hengtong Lu
Beijing University of Posts and Telecommunications
2 shared publications - Jiashen Sun
Meituan
2 shared publications - Lucen Zhong
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100083, China
2 shared publications - Xiaojie Wang
Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 4 November 2026
- Published by MDPI AG in Preprints.org
When, Where, and How Experience Becomes Structure: Mechanisms for Recursive Self-Improvement in LLM Agents
Recursive self-improvement (RSI) studies how AI systems modify themselves and carry those changes into the generation of subsequent improvements. LLM agents can pursue this process by using interaction experience to revise Prompt, Memory, Skill, and Harness in some cases while keeping the task-execution model’s weights fixed. However, execution feedback does not directly specify which component should change, and a locally successful revision may not remain useful across tasks or subsequent improvement cycles. Understanding how experience becomes persistent agent structure therefore requires examining when evidence justifies a change, where that change should act, and how it is constructed, verified, and retained. This survey connects four components--Prompt, Memory, Skill, and Harness--with seven analytical functions: Collect, Evaluate, Diagnose, Abstract, Update, Verify, and Consolidate. The resulting framework supports comparisons of instruction revision, memory management, skill construction and maintenance, and Harness evolution through their update loops. These comparisons examine how mechanisms use observations to construct candidate changes, distinguishing feedback that triggers revision from evidence that supports retention. The analysis further addresses coordinated updates across components and the revision or retirement of retained components as tasks, tools, and models change. Finally, we identify cross-component attribution, long-term effectiveness, and independent validation as key challenges, and outline controlled and longitudinal evaluations of task-performance gains, the contribution of inherited state, and the effectiveness of subsequent updates.
- 4 November 2026
- Published by MDPI AG in Preprints.org
Open AccessWhen, Where, and How Experience Becomes Structure: Mechanisms for Recursive Self-Improvement in LLM Agents
Recursive self-improvement (RSI) studies how AI systems modify themselves and carry those changes into the generation of subsequent improvements. LLM agents can pursue this process by using interaction experience to revise Prompt, Memory, Skill, and Harness in some cases while keeping the task-execution model’s weights fixed. However, execution feedback does not directly specify which component should change, and a locally successful revision may not remain useful across tasks or subsequent improvement cycles. Understanding how experience becomes persistent agent structure therefore requires examining when evidence justifies a change, where that change should act, and how it is constructed, verified, and retained. This survey connects four components--Prompt, Memory, Skill, and Harness--with seven analytical functions: Collect, Evaluate, Diagnose, Abstract, Update, Verify, and Consolidate. The resulting framework supports comparisons of instruction revision, memory management, skill construction and maintenance, and Harness evolution through their update loops. These comparisons examine how mechanisms use observations to construct candidate changes, distinguishing feedback that triggers revision from evidence that supports retention. The analysis further addresses coordinated updates across components and the revision or retirement of retained components as tasks, tools, and models change. Finally, we identify cross-component attribution, long-term effectiveness, and independent validation as key challenges, and outline controlled and longitudinal evaluations of task-performance gains, the contribution of inherited state, and the effectiveness of subsequent updates.
- 29 November 2024
- Published by Springer Nature
- p. 540-554
Pattern Shifting or Knowledge Losing? A Forgetting Perspective for Understanding the Effect of Instruction Fine-Tuning
- 29 November 2024
- Published by Springer Nature
- p. 540-554
Pattern Shifting or Knowledge Losing? A Forgetting Perspective for Understanding the Effect of Instruction Fine-Tuning
- 8 October 2023
- Published by Springer Nature
- p. 3-15
A Task-Oriented Dialog Model with Task-Progressive and Policy-Aware Pre-training
- 8 October 2023
- Published by Springer Nature
- p. 3-15
A Task-Oriented Dialog Model with Task-Progressive and Policy-Aware Pre-training
- Open Access
A Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training
Pre-trained conversation models (PCMs) have achieved promising progress in recent years. However, existing PCMs for Task-oriented dialog (TOD) are insufficient for capturing the sequential nature of the TOD-related tasks, as well as for learning dialog policy information. To alleviate these problems, this paper proposes a task-progressive PCM with two policy-aware pre-training tasks. The model is pre-trained through three stages where TOD-related tasks are progressively employed according to the task logic of the TOD system. A global policy consistency task is designed to capture the multi-turn dialog policy sequential relation, and an act-based contrastive learning task is designed to capture similarities among samples with the same dialog policy. Our model achieves better results on both MultiWOZ and In-Car end-to-end dialog modeling benchmarks with only 18\% parameters and 25\% pre-training data compared to the previous state-of-the-art PCM, GALAXY.
Open AccessA Task-oriented Dialog Model with Task-progressive and Policy-aware Pre-training
Pre-trained conversation models (PCMs) have achieved promising progress in recent years. However, existing PCMs for Task-oriented dialog (TOD) are insufficient for capturing the sequential nature of the TOD-related tasks, as well as for learning dialog policy information. To alleviate these problems, this paper proposes a task-progressive PCM with two policy-aware pre-training tasks. The model is pre-trained through three stages where TOD-related tasks are progressively employed according to the task logic of the TOD system. A global policy consistency task is designed to capture the multi-turn dialog policy sequential relation, and an act-based contrastive learning task is designed to capture similarities among samples with the same dialog policy. Our model achieves better results on both MultiWOZ and In-Car end-to-end dialog modeling benchmarks with only 18\% parameters and 25\% pre-training data compared to the previous state-of-the-art PCM, GALAXY.