256 citations · 323 across the 39 of their papers we have counts for
43 papers
SWE-Shift: Evaluating Coding Agents in Evolving Workspaces
Victor Shea-Jay Huang, Rongqing Li, Zhangyue Yin +7
Repository-level coding benchmarks largely assume that tasks and environments remain unchanged throughout execution. In software development, code, dependencies, runtime state, and…
PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis
Qiushi Sun, Jingyang Gong, Yang Liu +14
Multimodal code intelligence connects the symbolic world of programs with the visual world their execution creates. Interest in this capability is burgeoning, as models are increas…
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
Boyang Liu, Senjie Jin, Peixin Wang +17
Reliable search requires more than acquiring external evidence. An agent must also recognize and recover from errors as its trajectory unfolds. In-trajectory feedback provides a me…
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
Qiushi Sun, Kanzhi Cheng, Yian Wang +20
Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's actions, states, and reasoning. Verifying whether it fulfilled the…
HyperLogic: A Hard, Forward-Authored Chinese Logical Reasoning Benchmark with Execution-Derived Answers
Ming Zhang, Qiyuan Peng, Yinxi Wei +16
Existing logic benchmarks primarily measure models' ability to answer reasoning questions directly. Scalable benchmarks often generate text from formal structures, which makes answ…
CL-bench Life: Can Language Models Learn from Real-Life Context?
Shihan Dou, Yujiong Shen, Chenhao Huang +35
Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move be…
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
Zhiyuan Zeng, Jiameng Huang, Zhangyue Yin +8
Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is…
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
Yuan Li, Bo Wang, Yufei Gao +4
Proximal constraints are fundamental to the stability of the Large Language Model reinforcement learning. While the canonical clipping mechanism in PPO serves as an efficient surro…
CL-bench: A Benchmark for Context Learning
Shihan Dou, Ming Zhang, Zhangyue Yin +24
Current language models (LMs) excel at reasoning over prompts using pre-trained knowledge. However, real-world tasks are far more complex and context-dependent: models must learn f…
OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions
Hang Yan, Fangzhi Xu, Qiushi Sun +14
The advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments. However, existing evaluations primari…
OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment
Ming Zhang, Kexin Tan, Yueyuan Huang +20
Evaluating novelty is critical yet challenging in peer review, as reviewers must assess submissions against a vast, rapidly evolving literature. This report presents OpenNovelty, a…
RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization
Zeng Zhiyuan, Jiashuo Liu, Zhangyue Yin +3
While Reinforcement Learning for Verifiable Rewards (RLVR) is powerful for training large reasoning models, its training dynamics harbor a critical challenge: RL overfitting, where…
ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models
Zhangyue Yin, Qiushi Sun, Zhiyuan Zeng +4
Test-time scaling has emerged as a transformative paradigm for enhancing the performance of large reasoning models, enabling dynamic allocation of computational resources during in…
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
Qiushi Sun, Mukai Li, Zhoumianze Liu +11
Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents…
VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction
Jie Yang, Jiajun Chen, Zhangyue Yin +7
Intelligent vehicle cockpits present unique challenges for API Agents, requiring coordination across tightly-coupled subsystems that exceed typical task environments' complexity. T…
Dynamic and Generalizable Process Reward Modeling
Zhangyue Yin, Qiushi Sun, Zhiyuan Zeng +3
Process Reward Models (PRMs) are crucial for guiding Large Language Models (LLMs) in complex scenarios by providing dense reward signals. However, existing PRMs primarily rely on h…
FamilyTool: A Multi-hop Personalized Tool Use Benchmark
Yuxin Wang, Yiran Guo, Yining Zheng +7
The integration of tool learning with Large Language Models (LLMs) has expanded their capabilities in handling complex tasks by leveraging external tools. However, existing benchma…
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
Yuan Li, Qi Luo, Xiaonan Li +7
Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and mitigate hallucination. However, dense retri…
ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows
Qiushi Sun, Zhoumianze Liu, Chang Ma +18
Large Language Models (LLMs) have extended their impact beyond Natural Language Processing, substantially fostering the development of interdisciplinary research. Recently, various…
Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning
Jingqi Tong, Jixin Tang, Hangcheng Li +21
Vision-language reinforcement learning (RL) has primarily focused on narrow domains (e.g. geometry or chart reasoning). This leaves broader training scenarios and resources underex…
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
Zhiyuan Zeng, Qinyuan Cheng, Zhangyue Yin +2
The advent of test-time scaling in large language models (LLMs), exemplified by OpenAI's o1 series, has advanced reasoning capabilities by scaling computational resource allocation…
Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework
Yuhong Sun, Zhangyue Yin, Xuanjing Huang +2
Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. Math Word Problems (MWPs) serve as a crucial benchmark for evaluating LLMs' reasoning…
VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks
Shiduo Zhang, Zhe Xu, Peiju Liu +8
General-purposed embodied agents are designed to understand the users' natural instructions or intentions and act precisely to complete universal tasks. Recently, methods based on…
Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
Zhiyuan Zeng, Qinyuan Cheng, Zhangyue Yin +6
OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning ability.Op…