111 citations · 149 across the 14 of their papers we have counts for
17 papers
Augment the Cache, Replace the Activation: A 2x2 Study of Internal-State Sharing
Adam Deng, Shicheng Liu, Yada Zhu
Multi-agent systems built from frozen language models communicate through text, which discards the internal state the sender already computed and makes the receiver pay to rebuild…
Close Enough is Nowhere Near: Fidelity-Consumability Decoupling in KV Caches
Adam Deng, Shicheng Liu, Yada Zhu
Multi-agent LLM systems communicate in text, which is lossy and wasteful: the sender throws away the reading it already did. A growing literature instead transmits the KV cache, th…
Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization
Yue Mao, Shicheng Liu, Siyuan Xu +1
Inverse reinforcement learning (IRL) learns a reward function and a corresponding policy that best fit the demonstration data of an expert. However, in the current IRL setting, the…
DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling
Shicheng Liu, Yucheng Jiang, Sajid Farook +3
Deep research with Large Language Model (LLM) agents is emerging as a powerful paradigm for multi-step information discovery, synthesis, and analysis. However, existing approaches…
Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
Jiaxi Yang, Shicheng Liu, Yuchen Yang +1
With the rapid advancement of Vision Language Models (VLMs), refusal mechanisms have become a critical component for ensuring responsible and safe model behavior. However, existing…
Explainable reinforcement learning from human feedback to improve alignment
Shicheng Liu, Siyuan Xu, Wenjie Qiu +2
A common and effective strategy for humans to improve an unsatisfactory outcome in daily life is to find a cause of this outcome and correct the cause. In this paper, we investigat…
The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback
Hangfan Zhang, Siyuan Xu, Zhimeng Guo +8
Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial effo…
SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
Shicheng Liu, Kai Sun, Lisheng Fu +8
Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and reliably extract…
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
Junhong Lin, Shicheng Liu, Jinyeop Song +3
Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide…
Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring
Junyu Xue, Xudong Wang, Xiaoling He +3
Non-intrusive load monitoring (NILM) aims to disaggregate total electricity consumption into individual appliance usage, thus enabling more effective energy management. While deep…
In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates
Shicheng Liu, Minghui Zhu
Inverse reinforcement learning (IRL) aims to learn a reward function and a corresponding policy that best fit the demonstrated trajectories of an expert. However, current IRL works…
A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges
Guiliang Liu, Sheng Xu, Shicheng Liu +3
Inverse Constrained Reinforcement Learning (ICRL) is the task of inferring the implicit constraints that expert agents adhere to, based on their demonstration data. As an emerging…
SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions
Shicheng Liu, Sina J. Semnani, Harold Triedman +3
Large Language Models (LLMs) have led to significant improvements in the Knowledge Base Question Answering (KBQA) task. However, datasets used in KBQA studies do not capture the tr…
Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets
Harshit Joshi, Shicheng Liu, James Chen +2
Large Language Models can carry out human-like conversations in diverse settings, responding to user requests for tasks and knowledge. However, existing conversational agents imple…
Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning
Jun Feng, Heng Li, Minlie Huang +4
Ranking is a fundamental and widely studied problem in scenarios such as search, advertising, and recommendation. However, joint optimization for multi-scenario ranking, which aims…
Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks
Yabo Ni, Dan Ou, Shichen Liu +4
Tasks such as search and recommendation have become increas- ingly important for E-commerce to deal with the information over- load problem. To meet the diverse needs of di erent u…
Cascade Ranking for Operational E-commerce Search
Shichen Liu, Fei Xiao, Wenwu Ou +1
In the 'Big Data' era, many real-world applications like search involve the ranking problem for a large number of items. It is important to obtain effective ranking results and at…