10 papers
SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications
Zhengxi Li, Junyi Zhou, Qiyuan Zhang +6
Evaluating an agent's ability to strictly satisfy diverse and procedurally complex requirements is essential to determining its practical reliability. Conducting such an evaluation…
WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions
Junyi Zhou, Yufei Wang, Qiyuan Zhang +7
Developing terminal-based agents for long-horizon execution demands synthetic tasks that tightly couple complex instructions with authentic, interactive environments. However, curr…
HiMed: Incentivizing Hindi Reasoning in Medical LLMs
Dingfeng Jiang, Han Yan, Chenze Ma +12
Medical large language models hold promise for reducing healthcare disparities, yet Hindi remains severely underrepresented. While medical LLMs excel in high-resource languages, th…
Foundation Protocol: A Coordination Layer for Agentic Society
Bang Liu, Yongfeng Gu, Jiayi Zhang +26
Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly interact with one another. A…
PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
Shengyin Sun, Yiming Li, Renxi Liu +7
Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences. Although dLLMs can predict all masked positions in parallel within each step,…
Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward
Shizhan Gong, Minda Hu, Qiyuan Zhang +2
Vision-language models (VLMs) have achieved remarkable success across diverse tasks. However, concerns about their trustworthiness persist, particularly regarding tendencies to lea…
RubricBench: Aligning Model-Generated Rubrics with Human Standards
Qiyuan Zhang, Junyi Zhou, Yufei Wang +8
As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided ev…
Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models
Qiyuan Zhang, Yufei Wang, Tianhe Wu +5
Recent advancements in Generative Reward Models (GRMs) have demonstrated that scaling the length of Chain-of-Thought (CoT) reasoning considerably enhances the reliability of evalua…
JuDi: Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence
Shengyin Sun, Yiming Li, Renxi Liu +5
Judge Decoding accelerates LLM inference by relaxing the strict verification of Speculative Decoding, yet it typically relies on expensive and noisy supervision. In this work, we r…
Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
Shengyin Sun, Yiming Li, Xing Li +8
Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources durin…