14 papers
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders
Zhongyuan Peng, Dan Huang, Chuyu Zhang +8
The recent emergence of vibe-coding workflows is changing what coding agents are expected to do. Instead of merely completing code under fully specified instructions, agents are in…
Does the Same Token Mean the Same State? MoE Routing as Signal for Reasoning Control
Kang Chen, Minshen Yu, Junjie Nian +3
In sparse Mixture-of-Experts language models, does the same token id imply the same router state and the same experts producing it? Holding the emitted token id fixed at repeated a…
DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes
Caijun Xu, Changyi Xiao, Zhongyuan Peng +1
Reinforcement learning has become a central paradigm for advancing reasoning in large language models, yet most existing methods still depend on stronger teacher models or heavily…
DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model
Shibo Hong, Boxian Ai, Jun Kuang +5
Significant progress has been made in the field of Instruction-based Image Editing Models (IIEMs). However, while these models demonstrate plausible adherence to instructions and s…
SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning
Caijun Xu, Changyi Xiao, Zhongyuan Peng +2
Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain inf…
Reinforcement Learning with Conditional Expectation Reward
Changyi Xiao, Caijun Xu, Yixin Cao
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective in enhancing the reasoning capabilities of large language models, particularly in domains such as mathema…