5 citations · 9 across the 15 of their papers we have counts for
18 papers
Failure Is the Mother of Success: Recovering Supervision with Grounding Hindsight
Sheldon Yu, Tong Yu, Nikki Lijing Kuang +6
When every rollout for a problem fails, GRPO receives neither a successful exemplar nor a nonzero group-relative advantage, so it learns nothing from exactly the problems it most n…
Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning
Yuqing Zhou, Hong Wang, Manqing Mao +8
Large reasoning models can produce correct yet unnecessarily long reasoning traces. Existing methods improve reasoning efficiency with trajectory-level objectives or local token- a…
Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis
Manqing Mao, Hong Wang, Samson Koelle +8
Prompt-policy editing offers a practical way to improve agents that synthesize executable workflows without updating the underlying model. However, persistent prompt editing has tw…
ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent Research
Soyoung Yoon, Boyi Liu, Yite Wang +6
Multi-agent systems have shown strong performance in domains with reliable verifiers such as coding, where multi-parallel candidate generation selected by a verifier is effective.…
Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning
Zheyuan Zhang, Manqing Mao, Hong Wang +8
Critic-free group-based reinforcement learning has become a scalable approach for post-training large language models. However, most existing methods allocate the same number of ro…
RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts
Yuxin Xiong, Xunyi Jiang, Rohan Surana +8
Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback, where sampled rollouts can be compared within a group u…
Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows
Tianyang Liu, Canwen Xu, Fangyu Lei +6
Major cloud data platforms now expose large language model capabilities as native SQL functions, enabling analysts to perform classification, filtering, sentiment analysis, extract…
Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents
Hao-Lun Hsu, Nikki Lijing Kuang, Boyi Liu +2
Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input conte…
Co-Evolving Skill Generation and Policy Optimization
Zhiwei Zhang, Yudi Lin, Nikki Lijing Kuang +4
Skill-augmented reinforcement learning improves language agents by storing reusable procedural knowledge acquired from past experience. Existing methods typically use strong langua…
Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents
Yibo Wang, Nikki Lijing Kuang, Philip S. Yu +2
Interactive text-to-SQL agents solve database tasks through multi-turn interactions involving schema exploration, query execution, feedback interpretation, and decision revision. L…
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents
Sheldon Yu, Junda Wu, Xintong Li +6
Large language model agents interleave reasoning, action selection, and observation to solve sequential decision-making tasks. In deployed settings where agents repeatedly handle r…
Skill-R1: Agent Skill Evolution via Reinforcement Learning
Yash Vishe, Rohan Surana, Xunyi Jiang +8
Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved throu…
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
Rohan Surana, Gagan Mundada, Xunyi Jiang +19
Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these systems, the rollout, the trajec…
Performance Effectiveness of Multimedia Information Search Using the Epsilon-Greedy Algorithm
Nikki Lijing Kuang, Clement H. C. Leung
In the search and retrieval of multimedia objects, it is impractical to either manually or automatically extract the contents for indexing since most of the multimedia contents are…
Analysis of Evolutionary Behavior in Self-Learning Media Search Engines
Nikki Lijing Kuang, Clement H. C. Leung
The diversity of intrinsic qualities of multimedia entities tends to impede their effective retrieval. In a SelfLearning Search Engine architecture, the subtle nuances of human per…
Leveraging Reinforcement Learning Techniques for Effective Policy Adoption and Validation
Nikki Lijing Kuang, Clement H. C. Leung
Rewards and punishments in different forms are pervasive and present in a wide variety of decision-making scenarios. By observing the outcome of a sufficient number of repeated tri…
Performance Dynamics and Termination Errors in Reinforcement Learning: A Unifying Perspective
Nikki Lijing Kuang, Clement H. C. Leung
In reinforcement learning, a decision needs to be made at some point as to whether it is worthwhile to carry on with the learning process or to terminate it. In many such situation…
Stochastic Reinforcement Learning
Nikki Lijing Kuang, Clement H. C. Leung, Vienne W. K. Sung
In reinforcement learning episodes, the rewards and punishments are often non-deterministic, and there are invariably stochastic elements governing the underlying situation. Such s…