REVIEW 10 cited by
MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Recently, the astonishing performance of large language models (LLMs) in natural language comprehension and generation tasks triggered lots of exploration of using them as central controllers to build agent systems. Multiple studies focus on bridging the LLMs to external tools to extend the application scenarios. However, the current LLMs' ability to perceive tool use is limited to a single text query, which may result in ambiguity in understanding the users' real intentions. LLMs are expected to eliminate that by perceiving the information in the visual- or auditory-grounded instructions. Therefore, in this paper, we propose MLLM-Tool, a system incorporating open-source LLMs and multi-modal encoders so that the learned LLMs can be conscious of multi-modal input instruction and then select the function-matched tool correctly. To facilitate the evaluation of the model's capability, we collect a dataset featuring multi-modal input tools from HuggingFace. Another essential feature of our dataset is that it also contains multiple potential choices for the same instruction due to the existence of identical functions and synonymous functions, which provides more potential solutions for the same query. The experiments reveal that our MLLM-Tool is capable of recommending appropriate tools for multi-modal instructions. Codes and data are available at https://github.com/MLLM-Tool/MLLM-Tool.
Forward citations
Cited by 10 Pith papers
-
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
All-Angles Bench, a 2,132-question benchmark across 90 real scenes, shows current MLLMs score around 60% on multi-view understanding while humans score 82%, with the largest gaps in camera pose estimation and cross-vi...
-
MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning
A new one-million-sample multimodal agent tuning dataset with GPT-4o-generated rationales, reflection, and tool/RAG calls is shown to improve fine-tuned models, though training/eval benchmark overlap is not addressed.
-
MassTool: A Multi-Task Search-Based Tool Retrieval Framework for Large Language Models
A multi-task retriever that combines tool-usage detection with query-centered graph and search-based modules improves tool retrieval accuracy over prior baselines.
-
MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models
A synthetic music sheet QA dataset and a LoRA-fine-tuned Phi-3 model show large accuracy gains on OMR and chord tasks, but only within the synthetic distribution.
-
How Well Can Modern LLMs Act as Agent Cores in Radiology Environments?
Large language models complete only 29-67% of simulated radiology agent tasks, and prompting tricks and a simulated tool builder do not close the gap on complex workflows.
-
MageBench: Bridging Large Multimodal Models to Agents
MageBench introduces a 483-scenario benchmark showing current large multimodal models are far weaker than humans at agent tasks requiring continuous visual feedback and planning.
-
Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
SPORT builds a multimodal tool agent by generating synthetic tasks, sampling candidate tool calls, and tuning the agent on AI-verified step preferences, improving GTA and GAIA accuracy over the MAT baseline.
-
SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement
SurgVisAgent combines a ResNet distortion-prior with GPT-4o chain-of-thought reasoning to classify distortion type and severity and invoke the appropriate enhancement model, outperforming single-task models on a synth...
-
Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches
This survey argues that embodiment, symbol grounding, causality, and memory are the foundational principles needed to make large language models achieve artificial general intelligence.
-
Visual Large Language Models for Generalized and Specialized Applications
This paper reviews and taxonomizes VLLM applications into vision-to-text, vision-to-action, and text-to-vision, adding ethics and future-work discussion.
Discussion (0). Continue with ORCID to comment.