15 citations · 15 across the 9 of their papers we have counts for
11 papers
RSIGym: A Flexible Environment for Recursive Self-Improvement
Fanqing Meng, Lingxiao Du, Haocheng Lu +6
Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying agent-proposed changes also requires substantial research infrastructure…
Gödel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement
Ziqi Zhao, Fanqing Meng, Haocheng Lu +4
Recursive self-improvement (RSI) aims to achieve compounding gains by having models improve themselves. While most existing RSI systems optimize external agent harnesses or prompts…
RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
Fanqing Meng, Lingxiao Du, Qiguang Chen +4
Recursive self-improvement requires turning evidence of model failures into better models. Data-centric post-training research entails diagnosing capability gaps, designing and val…
Beyond Imitation: Reflective On-Policy Self-Distillation for LLM Reasoning
Ziqi Zhao, Xinyu Ma, Liu Yang +6
On-policy self-distillation (OPSD) improves the reasoning capabilities of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, e…
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
Fanqing Meng, Lingxiao Du, Zijian Wu +46
Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surrounding environment may change in…
Curriculum Approximate Unlearning for Session-based Recommendation
Liu Yang, Zhaochun Ren, Ziqi Zhao +7
Approximate unlearning for session-based recommendation refers to eliminating the influence of specific training samples from the recommender without retraining of (sub-)models. Gr…
Improving Sequential Recommenders through Counterfactual Augmentation of System Exposure
Ziqi Zhao, Zhaochun Ren, Jiyuan Yang +7
In sequential recommendation (SR), system exposure refers to items that are exposed to the user. Typically, only a few of the exposed items would be interacted with by the user. Al…
A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition
Zihan Wang, Ziqi Zhao, Yougang Lyu +3
Zero-shot named entity recognition (NER) aims to develop entity recognition systems from unannotated text corpora. This task presents substantial challenges due to minimal human in…
Offline Trajectory Optimization for Offline Reinforcement Learning
Ziqi Zhao, Zhaochun Ren, Liu Yang +6
Offline reinforcement learning (RL) aims to learn policies without online explorations. To enlarge the training data, model-based offline RL learns a dynamics model which is utiliz…
On the Effectiveness of Unlearning in Session-Based Recommendation
Xin Xin, Liu Yang, Ziqi Zhao +4
Session-based recommendation predicts users' future interests from previous interactions in a session. Despite the memorizing of historical samples, the request of unlearning, i.e.…
Generalizing Few-Shot Named Entity Recognizers to Unseen Domains with Type-Related Features
Zihan Wang, Ziqi Zhao, Zhumin Chen +3
Few-shot named entity recognition (NER) has shown remarkable progress in identifying entities in low-resource domains. However, few-shot NER methods still struggle with out-of-doma…