565 citations · 691 across the 38 of their papers we have counts for
42 papers
E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch
Hantian Ding, Chloe Bi, Jiacheng Zhu +5
Coding agents powered by large language models (LLMs) are evolving from making localized code changes to developing complete software repositories. However, evaluating repository-s…
StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models
Siyu Xu, Yunke Wang, Zijian Wang +6
Vision-Language-Action (VLA) models can follow instructions and manipulate objects, but their performance often collapses out of distribution (OOD), when the scene, viewpoint, or o…
Making AI Scientists Auditable from Evidence to Claim
Zijian Wang, Hanqi Li, Ziyue Yang +17
AI research systems can report improved results without establishing that the tested implementation matches the method described in their conclusions. We introduce Xcientist, a res…
Humans are Missing from AI Coding Agent Research
Zora Z. Wang, John Yang, Kilian Lieret +10
Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering tasks, from editing large codebase…
XFlow: An Executable Protocol Programming System for Reliable Multi-Agent Workflows
Hanqi Li, Jing Peng, Zijian Wang +2
LLM-based multi-agent systems increasingly coordinate planning, reasoning, tool use, and human interaction, yet their reliability remains limited. A central source of this limitati…
Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA
Sunah O, Jay-Yoon Lee
In multimodal multi-hop question answering, we focus on the initial retrieval stage via two distinct tasks: (1) evidence set completion, retrieving missing evidence given context,…
DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability
Ziyue Yang, Da Ma, Hanqi Li +8
As scientific literature grows rapidly and research increasingly involves AI agents, automated survey generation has become a key capability for both agents and human researchers.…
EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation
Jiajun Cao, Xiaoan Zhang, Xiaobao Wei +10
Vision-Language-Action models have shown great promise for autonomous driving, yet they suffer from degraded perception after unfreezing the visual encoder and struggle with accumu…
SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
Patrick Tser Jern Kon, Archana Pradeep, Ang Chen +5
Small language models (SLMs) offer compelling advantages in cost, latency, and adaptability, but have so far lagged behind larger models on long-horizon software engineering tasks…
Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
Amrith Setlur, Zijian Wang, Andrew Cohen +2
Typical reinforcement learning (RL) methods for LLM reasoning waste compute on hard problems, where correct on-policy traces are rare, policy gradients vanish, and learning stalls.…
PaperGuide: Making Small Language-Model Paper-Reading Agents More Efficient
Zijian Wang, Tiancheng Huang, Hanqi Li +3
The accelerating growth of the scientific literature makes it increasingly difficult for researchers to track new advances through manual reading alone. Recent progress in large la…
ThinkDrive: Chain-of-Thought Guided Progressive Reinforcement Learning Fine-Tuning for Autonomous Driving
Chang Zhao, Zheming Yang, Yunqing Hu +4
With the rapid advancement of large language models (LLMs) technologies, their application in the domain of autonomous driving has become increasingly widespread. However, existing…
Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation
Siyu Xu, Zijian Wang, Yunke Wang +3
Vision-Language-Action (VLA) models have shown great performance in robotic manipulation by mapping visual observations and language instructions directly to actions. However, they…
Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization
Zijian Wang, Yanxiang Ma, Chang Xu
Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on gene…
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
Yifeng Ding, Hung Le, Songyang Han +5
Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challe…
Controllable Flow Matching for Online Reinforcement Learning
Bin Wang, Boxiang Tao, Haifeng Jing +2
Model-based reinforcement learning (MBRL) typically relies on modeling environment dynamics for data efficiency. However, due to the accumulation of model errors over long-horizon…
Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs
Jiahao Liu, Zijian Wang, Kuo Zhao +1
Knowledge editing has emerged as an efficient approach for updating factual knowledge in large language models (LLMs). It typically locates knowledge storage modules and then modif…
ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations
Zijian Wang, Chang Xu
This paper introduces ThoughtProbe, a novel inference time framework that leverages the hidden reasoning features of Large Language Models (LLMs) to improve their reasoning perform…
CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation
Kaiwen Wei, Xiao Liu, Jie Zhang +11
Multimodal Retrieval-Augmented Generation (MRAG) enables Multimodal Large Language Models (MLLMs) to generate responses with external multimodal evidence, and numerous video-based…
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Terry Yue Zhuo, Xiaolong Jin, Hange Liu +37
Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain,…
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
Shoumik Saha, Jifan Chen, Sam Mayers +3
Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-o…
Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
Terry Yue Zhuo, Dingmin Wang, Hantian Ding +2
Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excelling at software engineering tasks through…
AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluation
Tiancheng Huang, Ruisheng Cao, Yuxin Zhang +8
The growing volume of academic papers has made it increasingly difficult for researchers to efficiently extract key information. While large language models (LLMs) based agents are…
Cyber-Zero: Training Cybersecurity Agents without Runtime
Terry Yue Zhuo, Dingmin Wang, Hantian Ding +2
Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issu…