13 citations · 14 across the 11 of their papers we have counts for
14 papers
CompoWorld: Compositional Environment Scaling for General Agents
Xiao-Wen Yang, Weiyi Xu, Wen Da +9
Automatically generated environments provide a scalable source of interaction data for training general agents. However, existing approaches mainly generate tasks within a single e…
Revisiting the Travel Planning Capabilities of Large Language Models
Bo-Wen Zhang, Jin Ye, Peng-Yu Hua +4
Travel planning serves as a critical task for long-horizon reasoning, exposing significant deficits in LLMs. However, existing benchmarks and evaluations primarily assess final pla…
Programmatic Context Augmentation for LLM-based Symbolic Regression
Hao Liu, Xiao-Wen Yang, Atharva Sehgal +4
Symbolic regression (SR), the task of discovering mathematical expressions that best describe a given dataset, remains a fundamental challenge in scientific discovery. Traditional…
Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
Jie-Jing Shao, Haiyan Yin, Yueming Lyu +5
Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mit…
Activation Compression in LLMs: Theoretical Analysis and Efficient Algorithm
Wen-Da Wei, Han-Bin Fang, Yang-Di Liu +3
Training large language models (LLMs) is highly memory-intensive, as training must store not only weights and optimizer states but also intermediate activations for backpropagation…
Hindsight Credit Assignment for Long-Horizon LLM Agents
Hui-Ze Tan, Xiao-Wen Yang, Hao Chen +7
Large Language Model (LLM) agents often face significant credit assignment challenges in long-horizon, multi-step tasks due to sparse rewards. Existing value-free methods, such as…
Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
Hong-Jie You, Jie-Jing Shao, Xiao-Wen Yang +3
Existing methods for expressive music performance rendering, a conditional generation task that aims to generate a human-like performance from a symbolic score, rely on supervised…
Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
Xiao-Wen Yang, Jie-Jing Shao, Lan-Zhe Guo +5
Large Language Models (LLMs) have shown promising results across various tasks, yet their reasoning capabilities remain a fundamental challenge. Developing AI systems with strong r…
Curriculum Abductive Learning
Wen-Chao Hu, Qi-Jie Li, Lin-Han Jia +4
Abductive Learning (ABL) integrates machine learning with logical reasoning in a loop: a learning model predicts symbolic concept labels from raw inputs, which are revised through…
Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible
Lin-Han Jia, Wen-Chao Hu, Jie-Jing Shao +2
The current Neuro-Symbolic (NeSy) Learning paradigm suffers from an over-reliance on labeled data, so if we completely disregard labels, it leads to less symbol information, a larg…
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models
Xiao-Wen Yang, Xuan-Yi Zhu, Wen-Da Wei +5
The integration of slow-thinking mechanisms into large language models (LLMs) offers a promising way toward achieving Level 2 AGI Reasoners, as exemplified by systems like OpenAI's…
Robust Semi-Supervised Learning in Open Environments
Lan-Zhe Guo, Lin-Han Jia, Jie-Jing Shao +1
Semi-supervised learning (SSL) aims to improve performance by exploiting unlabeled data when labels are scarce. Conventional SSL studies typically assume close environments where i…
ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents
Jie-Jing Shao, Bo-Wen Zhang, Xiao-Wen Yang +8
Travel planning stands out among real-world applications of \emph{Language Agents} because it couples significant practical demand with a rigorous constraint-satisfaction challenge…
Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation
Jie-Jing Shao, Hao-Ran Hao, Xiao-Wen Yang +1
Recent learning-to-imitation methods have shown promising results in planning via imitating within the observation-action space. However, their ability in open environments remains…