← Back to all news
arXiv AI By Min Wang, Ata Mahjoubfar

AMIGO: Agentic Multi-Image Grounding Oracle Benchmark

Read the original on arXiv AI →

AMIGO (Agentic Multi-Image Grounding Oracle Benchmark) is a long-horizon evaluation framework for vision‑language models that tests hidden‑target identification across galleries of visually similar images. The benchmark requires a model to ask a sequence of attribute‑focused Yes/No questions, receiving Yes/No/Unsure feedback and penalizing invalid actions with Skip, thereby stressing question selection under uncertainty, constraint tracking, and fine‑grained discrimination. Using the Guess My Preferred Dress task, the study shows that final‑answer accuracy alone overstates performance, as models may guess correctly without verified evidence, waste turns, or violate the protocol, highlighting the need for combined visual discrimination, informative questioning, and robust protocol adherence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jun 3

WildRoadBench: A Wild Aerial Road-Damage Grounding Benchmark for Vision-Language Models and Autonomous Agents

arXiv:2605. 20306v2 Announce Type: replace-cross Abstract: We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous research-and-engineering by LLM-driven agents on a single professionally annotated UAV corpus.

By Bingnan Liu, Chenhang Cui, Rui Huang, Jiani Luo, Zhirong Shen, Tinghao Wang, Xiande Huang, Lingbei Meng, Fei Shen, An Zhang
llmsagentsmultimodalbenchmarks
More like this →
arXiv Computer Vision
Aug 26

DoublesEval: Diagnosing Multi-Agent Tactical Reasoning in Vision-Language Models via Professional Doubles Badminton

The paper introduces DoublesEval, a diagnostic framework that uses professional doubles badminton to test visual‑language models’ ability to reason about dynamic multi‑agent interactions. It decomposes rallies into key moments and evaluates models across four dimensions—atomic recognition, intra‑segment composite understanding, cross‑segment causal reasoning, and high‑level tactical abstraction—highlighting specific reasoning failures. The authors also propose TacticCheck, a lightweight consistency checker that improves performance without retraining the models, yet significant gaps remain in tactical reasoning.

By Jintao Cheng, Weibin Li
llmsagentsmultimodal
More like this →
arXiv AI
Jun 16

ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering

arXiv:2606. 14772v1 Announce Type: cross Abstract: Aerial Embodied Question Answering (EQA) requires Unmanned Aerial Vehicles (UAVs) to actively perceive the environment and answer natural language questions.

By Wenhao Lu, Zhengqiu Zhu, Xiaofeng Wang, Xiaoran Zhang, Yatai Ji, Yong Zhao, Yue Hu, Yingzhen Nie, Jinlong Zhu, Zheng Zhu
diffusionnlproboticsmultimodalbenchmarks
More like this →
arXiv AI
Sep 4

Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models

The paper introduces the Necessary Tool‑Evidence Path (NTEP) annotation scheme and its associated reward mechanism (NTEP‑R) to better supervise vision‑language models that use external tools. By explicitly specifying which evidence is needed and penalizing redundant tool calls, the authors train an 8B‑parameter model that shows improved accuracy and tool‑use efficiency across seven image‑grounded benchmarks. The approach demonstrates that fine‑grained supervision of tool‑evidence paths is essential for robust agentic VLM performance.

By Xingming Long, Yu Liu, Zhiwei Yang, Hanqi Feng, Shaojie Zhang, Barnabas Poczos, Chao Jiang, Zhenbo Luo, Lei Jiang, Pei Fu
llmsagentsmultimodalbenchmarks
More like this →