Alfonso Amayuelas
@amayuelas.bsky.social
Check out the paper on arxiv if you're interested👇
Special appreciation to everyone who contributed to this project 🙏 Jingbo Yang, Saaket Agashe, Ashwin Nagarajan, Antonis Antoniades, @ericxw.bsky.social William Wang
arxiv.org/abs/2504.02051
🧵(3/3)
Special appreciation to everyone who contributed to this project 🙏 Jingbo Yang, Saaket Agashe, Ashwin Nagarajan, Antonis Antoniades, @ericxw.bsky.social William Wang
arxiv.org/abs/2504.02051
🧵(3/3)
Self-Resource Allocation in Multi-Agent LLM Systems
With the development of LLMs as agents, there is a growing interest in connecting multiple agents into multi-agent systems to solve tasks concurrently, focusing on their role in task assignment and co...
arxiv.org
April 17, 2025 at 6:46 PM
Check out the paper on arxiv if you're interested👇
Special appreciation to everyone who contributed to this project 🙏 Jingbo Yang, Saaket Agashe, Ashwin Nagarajan, Antonis Antoniades, @ericxw.bsky.social William Wang
arxiv.org/abs/2504.02051
🧵(3/3)
Special appreciation to everyone who contributed to this project 🙏 Jingbo Yang, Saaket Agashe, Ashwin Nagarajan, Antonis Antoniades, @ericxw.bsky.social William Wang
arxiv.org/abs/2504.02051
🧵(3/3)
We evaluate LLMs as orchestrators and planners in MAS, exploring their resource allocation. The planner method achieves better efficiency and utilization for concurrent tasks. Explicit info on worker capabilities enhances strategies, especially with suboptimal workers.
🧵(2/3)
🧵(2/3)
April 17, 2025 at 6:46 PM
We evaluate LLMs as orchestrators and planners in MAS, exploring their resource allocation. The planner method achieves better efficiency and utilization for concurrent tasks. Explicit info on worker capabilities enhances strategies, especially with suboptimal workers.
🧵(2/3)
🧵(2/3)
Check out the paper and website! 👇
📜Paper: arxiv.org/abs/2504.07072
🌐Website: dataset.ckodser.ir
📁Dataset: huggingface.co/datasets/Coh...
📜Paper: arxiv.org/abs/2504.07072
🌐Website: dataset.ckodser.ir
📁Dataset: huggingface.co/datasets/Coh...
arxiv.org
April 11, 2025 at 6:48 AM
Check out the paper and website! 👇
📜Paper: arxiv.org/abs/2504.07072
🌐Website: dataset.ckodser.ir
📁Dataset: huggingface.co/datasets/Coh...
📜Paper: arxiv.org/abs/2504.07072
🌐Website: dataset.ckodser.ir
📁Dataset: huggingface.co/datasets/Coh...
This work shows the potential of combining structured knowledge from KGs with LLMs' generative capabilities, enhancing reasoning while adding relevant domain-specific knowledge and explainability to answers anchored to entities in the graph (4/4)
📜🔗 arxiv.org/abs/2502.13247
📜🔗 arxiv.org/abs/2502.13247
Grounding LLM Reasoning with Knowledge Graphs
Knowledge Graphs (KGs) are valuable tools for representing relationships between entities in a structured format. Traditionally, these knowledge bases are queried to extract specific information. Howe...
arxiv.org
February 25, 2025 at 5:27 PM
This work shows the potential of combining structured knowledge from KGs with LLMs' generative capabilities, enhancing reasoning while adding relevant domain-specific knowledge and explainability to answers anchored to entities in the graph (4/4)
📜🔗 arxiv.org/abs/2502.13247
📜🔗 arxiv.org/abs/2502.13247
🔍ToT strategy excels by exploring multiple reasoning paths, leading to up to a 54.74% performance boost. Targeted interactions with KGs, like the agentic method, improve over time with more steps, while automatic graph exploration excels with fewer steps (3/4)
February 25, 2025 at 5:27 PM
🔍ToT strategy excels by exploring multiple reasoning paths, leading to up to a 54.74% performance boost. Targeted interactions with KGs, like the agentic method, improve over time with more steps, while automatic graph exploration excels with fewer steps (3/4)
The study shows significant improvements using different reasoning strategies (CoT, ToT, GoT) on the GRBench dataset. We compare the results for an agent solution vs an automatic graph search at every thought step (2/4)
February 25, 2025 at 5:27 PM
The study shows significant improvements using different reasoning strategies (CoT, ToT, GoT) on the GRBench dataset. We compare the results for an agent solution vs an automatic graph search at every thought step (2/4)