9 papers
VIEWCRAFT: Evolving What Multimodal Agents See and How They Read It
Binxiao Xu, Ruichuan An, Bocheng Zou +7
Reusable skills improve multimodal agents without updating model weights, but their effectiveness depends on both the evidence presented and the procedure used to read it. We intro…
SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition
Yuxuan Liu, Zhaochen Su, Hangyu Guo +11
Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evaluation is to expand task requir…
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
Lei Yang, Mengyin Liu, Jia Wang +9
We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as its core interaction: while r…
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
Yana Wei, Hongbo Peng, Yanlin Lai +14
We introduce PerceptionRubrics, a rubric-based evaluation framework that addresses the gap between saturated benchmark scores and real-world brittleness. Shifting evaluation from h…
WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics
Yuhong Dai, Yanlin Lai, Mitt Huang +9
Existing web-generation benchmarks rely on text prompts or static screenshots as input. However, videos naturally convey richer signals such as interaction flow, transition timing,…
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
Xiangfeng Wang, Hangyu Guo, Yanlin Lai +11
While model-based verifiers are essential for scaling Reinforcement Learning with Verifiable Rewards (RLVR), current outcome-centric verification paradigms primarily focus on the c…
R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging
Yanlin Lai, Mitt Huang, Hangyu Guo +11
Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts t…
STEP3-VL-10B Technical Report
Ailin Huang, Chengyuan Yao, Chunrui Han +90
We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-…