SimpleSearch-VL improves Qwen3-VL multimodal agent baselines by 15.8-16 points on average using 7K total training examples and reaches parity with Gemini-3-Pro on the 30B variant.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM agents execute network procedures via tool sequences; single-tool encapsulation cuts latency and errors compared with iterative reasoning, but all models lose reliability as procedure length grows.
citing papers explorer
-
SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search
SimpleSearch-VL improves Qwen3-VL multimodal agent baselines by 15.8-16 points on average using 7K total training examples and reaches parity with Gemini-3-Pro on the 30B variant.
-
Beyond State Machines: Executing Network Procedures with Agentic Tool-Calling Sequences
LLM agents execute network procedures via tool sequences; single-tool encapsulation cuts latency and errors compared with iterative reasoning, but all models lose reliability as procedure length grows.