17 citations · 50 across the 27 of their papers we have counts for
29 papers
Learning Stateful Predictive Knowledge From Experience
Yan Song, Xidong Feng, Bo Liu +7
As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights. Viewed through the lens of predicti…
See Better, Foresee Better, Act Wiser: Physically Grounded Proactive Modeling and Decision Making
Honghui Zhang, Anna Min, Chenmeinian Guo +9
Reliable proactive agents must choose an action and judge whether current evidence is sufficient to act. We study retail service from sparse third-person video: before an explicit…
Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
Qirui Mi, Zhijian Ma, Mengyue Yang +4
LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. This insufficient experience reuse…
Superficial Reflection or Genuine Thought? A Fine-Grained Cognitive Analysis of Large Reasoning Models
Yuxiang Chen, Zuohan Wu, Ziwei Wang +6
Motivated by the observed human-like behaviours in Large Reasoning Models (LRMs), this paper introduces a comprehensive taxonomy to characterise atomic reasoning steps and analyse…
A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
Anjie Liu, Jianhong Wang, Samuel Kaski +2
Steering cooperative multi-agent reinforcement learning (MARL) towards desired outcomes is challenging, particularly when the global guidance from a human on the whole multi-agent…
Memory-Driven Self-Improvement for Decision Making with Large Language Models
Xue Yan, Zijing Ou, Mengyue Yang +4
Large language models (LLMs) have emerged as effective action policies for sequential decision-making (SDM) tasks due to their extensive prior knowledge. However, this broad yet ge…
Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning
Danni Yang, Zhikang Chen, Sen Cui +6
Federated continual learning (FCL) has garnered increasing attention for its ability to support distributed computation in environments with evolving data distributions. However, t…
Large Language Models are Demonstration Pre-Selectors for Themselves
Jiarui Jin, Yuwei Wu, Haoxuan Li +6
In-context learning (ICL) with large language models (LLMs) delivers strong few-shot performance by choosing few-shot demonstrations from the entire training data. However, existin…
Curious Causality-Seeking Agents Learn Meta Causal World
Zhiyu Zhao, Haoxuan Li, Haifeng Zhang +4
When building a world model, a common assumption is that the environment has a single, unchanging underlying causal rule, like applying Newton's laws to every situation. In reality…
Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
Xiangning Yu, Zhuohan Wang, Linyi Yang +5
Chain-of-Thought (CoT) prompting plays an indispensable role in endowing large language models (LLMs) with complex reasoning capabilities. However, CoT currently faces two fundamen…
Estimating the Effects of Sample Training Orders for Large Language Models without Retraining
Hao Yang, Haoxuan Li, Mengyue Yang +2
The order of training samples plays a crucial role in large language models (LLMs), significantly impacting both their external performance and internal learning dynamics. Traditio…
MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework
Qirui Mi, Mengyue Yang, Xiangning Yu +6
Simulating collective decision-making involves more than aggregating individual behaviors; it emerges from dynamic interactions among individuals. While large language models (LLMs…
Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
Yongcheng Zeng, Xinyu Cui, Xuanfa Jin +11
Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement,…
Natural Language Reinforcement Learning
Xidong Feng, Bo Liu, Yan Song +7
Artificial intelligence progresses towards the "Era of Experience," where agents are expected to learn from continuous, grounded interaction. We argue that traditional Reinforcemen…
Efficient Reinforcement Learning with Large Language Model Priors
Xue Yan, Yan Song, Xidong Feng +4
In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases. However, they often require e…
Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games
Anjie Liu, Jianhong Wang, Haoxuan Li +4
In human-AI interaction, a prominent goal is to attain human`s desirable outcome with the assistance of AI agents, which can be ideally delineated as a problem of seeking the optim…
Learning Macroeconomic Policies through Dynamic Stackelberg Mean-Field Games
Qirui Mi, Zhiyu Zhao, Chengdong Ma +5
Macroeconomic outcomes emerge from individuals' decisions, making it essential to model how agents interact with macro policy via consumption, investment, and labor choices. We for…
Natural Language Reinforcement Learning
Xidong Feng, Ziyu Wan, Mengyue Yang +5
Reinforcement Learning (RL) has shown remarkable abilities in learning policies for decision-making tasks. However, RL is often hindered by issues such as low sample efficiency, la…
InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization
Jiarui Jin, Zexue He, Mengyue Yang +4
Ranking items regarding individual user interests is a core technique of multiple downstream tasks such as recommender systems. Learning such a personalized ranker typically relies…
Specify Robust Causal Representation from Mixed Observations
Mengyue Yang, Xinyu Cai, Furui Liu +2
Learning representations purely from observations concerns the problem of learning a low-dimensional, compact representation which is beneficial to prediction models. Under the hyp…
Lending Interaction Wings to Recommender Systems with Conversational Agents
Jiarui Jin, Xianyu Chen, Fanghua Ye +5
Recommender systems trained on offline historical user behaviors are embracing conversational techniques to online query user preference. Unlike prior conversational recommendation…
Invariant Learning via Probability of Sufficient and Necessary Causes
Mengyue Yang, Zhen Fang, Yonggang Zhang +5
Out-of-distribution (OOD) generalization is indispensable for learning models in the wild, where testing distribution typically unknown and different from the training. Recent meth…
Replace Scoring with Arrangement: A Contextual Set-to-Arrangement Framework for Learning-to-Rank
Jiarui Jin, Xianyu Chen, Weinan Zhang +5
Learning-to-rank is a core technique in the top-N recommendation task, where an ideal ranker would be a mapping from an item set to an arrangement (a.k.a. permutation). Most existi…
ChessGPT: Bridging Policy Learning and Language Modeling
Xidong Feng, Yicheng Luo, Ziyan Wang +6
When solving decision-making tasks, humans typically depend on information from two key sources: (1) Historical policy data, which provides interaction replay from the environment,…