BAMAS: Smarter AI Teams on a Budget

Kari Jaaskelainen

27 Nov 2025 — 1 min read

Smarter AI Teams, Smaller Bills: Meet BAMAS

Large language model (LLM) agent teams can tackle tough problems—but their cloud bills add up fast. BAMAS is a new method for building multi-agent systems that keeps performance high while respecting a budget.

How it works:

Pick the right mix of models. BAMAS formulates an integer linear program to balance accuracy and cost when choosing which LLMs to include.
Design how they talk. A reinforcement learning strategy selects the best interaction topology—who collaborates with whom and when.
Run the plan. The selected agents and topology are instantiated and executed for the task.

In tests across three representative tasks, BAMAS matched state-of-the-art approaches while cutting costs by up to 86%.

Paper by Liming Yang, Junyu Luo, Xuanzhe Liu, Yiling Lou, and Zhenpeng Chen. Read more: https://arxiv.org/abs/2511.21572v1

Paper: https://arxiv.org/abs/2511.21572v1

Register: https://www.AiFeta.com

#AI #LLM #MultiAgentSystems #ReinforcementLearning #Optimization #CostEfficiency #Research

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added