2 citations · 8 across the 13 of their papers we have counts for
10 papers · 1 filter
SWE-RM: Execution-free Feedback For Software Engineering Agents
KaShun Shum, Binyuan Hui, Jiawei Chen +6
Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm require…
Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification
Weihao Zeng, Keqing He, Chuqiao Kuang +2
Test-time compute can be scaled both sequentially and in parallel. Sequential scaling involves lengthening the generation process, while parallel scaling involves verifying and sel…
The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
Junlong Li, Wenshuo Zhao, Jian Zhao +18
Real-world language agents must handle complex, multi-step workflows across diverse Apps. For instance, an agent may manage emails by coordinating with calendars and file systems,…
WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
Junteng Liu, Yunji Li, Chi Zhang +12
The paradigm of Large Language Models (LLMs) has increasingly shifted toward agentic applications, where web browsing capabilities are fundamental for retrieving information from d…
Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions
Haoze Wu, Cheng Wang, Wenshuo Zhao +1
Recent advances in applying reinforcement learning (RL) to large language models (LLMs) have led to substantial progress. In particular, a series of remarkable yet often counterint…
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
Wei Liu, Ruochen Zhou, Yiyun Deng +5
Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces.…
From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning
Yuzhen Huang, Weihao Zeng, Xingshan Zeng +2
Trustworthy verifiers are essential for the success of reinforcement learning with verifiable reward (RLVR), which is the core methodology behind various large reasoning models suc…
SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
Weihao Zeng, Yuzhen Huang, Qian Liu +4
DeepSeek-R1 has shown that long chain-of-thought (CoT) reasoning can naturally emerge through a simple reinforcement learning (RL) framework with rule-based rewards, where the trai…
On the Perception Bottleneck of VLMs for Chart Understanding
Junteng Liu, Weihao Zeng, Xiwen Zhang +3
Chart understanding requires models to effectively analyze and reason about numerical data, textual elements, and complex visual components. Our observations reveal that the percep…
Predictive Data Selection: The Data That Predicts Is the Data That Teaches
Kashun Shum, Yuzhen Huang, Hongjian Zou +5
Language model pretraining involves training on extensive corpora, where data quality plays a pivotal role. In this work, we aim to directly estimate the contribution of data durin…