72 citations · 211 across the 32 of their papers we have counts for
33 papers
Inducing Process Supervision from Outcome-Only Reinforcement Learning
Shengda Fan, Xin Cong, Zhong Zhang +2
Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning. However, training strong PRMs r…
Benchmarking Language Models for Statistical Problem Formulation
Chen Wang, Junzhe Zhao, Xin Cong +2
Large language models (LLMs) are increasingly used as assistants for statistical and data science work, yet existing evaluations largely assume the analysis target is already speci…
Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement
Yufeng Han, Lifan Deng, Cunliang Kong +5
Classical Chinese poetry composition has long valued Tuiqiao, the iterative refinement of words, imagery, and prosody. However, many current AI poetry systems follow a one-shot gen…
What is Missing from AI Post-Training AI: An Empirical Analysis
Joy Jia Yin Lim, Xin Huang, Hao Peng +5
Large language model (LLM) agents can now post-train an LLM end-to-end, raising the prospect of recursive self-improvement (RSI). Yet this progress is measured by aggregate benchma…
Test-Time Deep Thinking to Explore Implicit Rules
Wentong Chen, Xin Cong, Zhong Zhang +8
With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by im…
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
Shengda Fan, Xuyan Ye, Yupeng Huo +9
While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often recti…
AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
Yishan Li, Wentong Chen, Yukun Yan +12
Generating deep research reports requires large-scale information acquisition and the synthesis of insight-driven analysis, posing a significant challenge for current language mode…
AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents
Haotian Chen, Xin Cong, Shengda Fan +16
While Large Language Model (LLM)-based agents have shown remarkable potential for solving complex tasks, existing systems remain heavily reliant on large-scale models, leaving the…
SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring…
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning
Zhong Zhang, Yaxi Lu, Yikun Fu +22
The recent progress of large language model agents has opened new possibilities for automating tasks through graphical user interfaces (GUIs), especially in mobile environments whe…
MiniCPM4: Ultra-Efficient LLMs on End Devices
MiniCPM Team, Chaojun Xiao, Yuxuan Li +80
This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in…
ToLeaP: Rethinking Development of Tool Learning with Large Language Models
Haotian Chen, Zijun Song, Boye Niu +8
Tool learning, which enables large language models (LLMs) to utilize external tools effectively, has garnered increasing attention for its potential to revolutionize productivity a…
Synergizing Large Language Models and Theory for Human-like Causal Reasoning
Yanxi Zhang, Xin Cong, Zhong Zhang +3
Performing causal reasoning akin to humans is fundamental to achieving strong artificial intelligence. However, existing studies on causal reasoning and large language models (LLMs…
Learning to Generate Structured Output with Schema Reinforcement Learning
Yaxi Lu, Haolun Li, Xin Cong +6
This study investigates the structured generation capabilities of large language models (LLMs), focusing on producing valid JSON outputs against a given schema. Despite the widespr…
AgentRM: Enhancing Agent Generalization with Reward Modeling
Yu Xia, Jingru Fan, Weize Chen +7
Existing LLM-based agents have achieved strong performance on held-in tasks, but their generalizability to unseen tasks remains poor. Hence, some recent work focus on fine-tuning t…
Which Type of Students can LLMs Act? Investigating Authentic Simulation with Graph-based Human-AI Collaborative System
Haoxuan Li, Jifan Yu, Xin Cong +6
While rapid advances in large language models (LLMs) are reshaping data-driven intelligent education, accurately simulating students remains an important but challenging bottleneck…
WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
Shengda Fan, Xin Cong, Yuepeng Fu +7
Recent advancements in large language models (LLMs) have driven a revolutionary paradigm shift in process automation from Robotic Process Automation to Agentic Process Automation b…
Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
Runchu Tian, Yanghao Li, Yuepeng Fu +10
Positional bias in large language models (LLMs) hinders their ability to effectively process long inputs. A prominent example is the "lost in the middle" phenomenon, where LLMs str…
Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
Yaxi Lu, Shenzhi Yang, Cheng Qian +12
Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scena…
Learning Evolving Tools for Large Language Models
Guoxin Chen, Zhong Zhang, Xin Cong +5
Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of…
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
Zhiyu Yang, Zihan Zhou, Shuo Wang +10
Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Des…
RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation
Qinyu Luo, Yining Ye, Shihao Liang +10
Generative models have demonstrated considerable potential in software engineering, particularly in tasks such as code generation and debugging. However, their utilization in the d…
Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents
Cheng Qian, Bingxiang He, Zhong Zhuang +8
Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. Although adep…
UniMem: Towards a Unified View of Long-Context Large Language Models
Junjie Fang, Likai Tang, Hongzhe Bi +12
Long-context processing is a critical ability that constrains the applicability of large language models (LLMs). Although there exist various methods devoted to enhancing the long-…