11 papers
DarwinX: Evolving Agent Harnesses Through Natural Selection
Yifan Zhang, Yutong Dai, Juntao Tan +9
An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops already edit harnesses, yet single-…
How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning
Luyu Yang, Yutong Dai, An Yan +3
The physical world is not merely visual; it is governed by rigorous structural and procedural constraints. Yet, the evaluation of vision-language models (VLMs) remains heavily skew…
UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG
Xiangyu Peng, Can Qin, Zeyuan Chen +3
Multimodal retrieval-augmented Generation (MM-RAG) is a key approach for applying large language models (LLMs) and agents to real-world knowledge bases, yet current evaluations are…
BLIP3o-NEXT: Next Frontier of Native Image Generation
Jiuhai Chen, Le Xue, Zhiyang Xu +12
We present BLIP3o-NEXT, a fully open-source foundation model in the BLIP3 series that advances the next frontier of native image generation. BLIP3o-NEXT unifies text-to-image gener…
WALT: Web Agents that Learn Tools
Viraj Prabhu, Yutong Dai, Matthew Fernandez +8
Web agents promise to automate complex browser tasks, but current methods remain brittle -- relying on step-by-step UI interactions and heavy LLM reasoning that break under dynamic…
SCUBA: Salesforce Computer Use Benchmark
Yutong Dai, Krithika Ramakrishnan, Jing Gu +8
We introduce SCUBA, a benchmark designed to evaluate computer-use agents on customer relationship management (CRM) workflows within the Salesforce platform. SCUBA contains 300 task…