AI

ToolOrchestra: Small AI that smartly manages tools

Kari Jaaskelainen

27 Nov 2025 — 1 min read

Large models are powerful, but solving deep, multi-step problems is pricey. ToolOrchestra trains a small “orchestrator” that decides which tools to use, when, and how—like a smart project manager for AI.

It uses reinforcement learning with rewards for outcomes, efficiency, and user preferences. The result: an 8B Orchestrator that beats bigger tool-use agents on tough benchmarks.

On Humanity’s Last Exam (HLE), it scores 37.1%, edging out GPT-5 at 35.1%, while ~2.5x more efficient.
On tau2-Bench and FRAMES, it outperforms GPT-5 at ~30% of the cost.
It generalizes to new tools and respects user tool choices.

Bottom line: coordinating many tools with a lightweight model can be smarter and cheaper than relying on one giant model.

Paper by Hongjin Su et al. Details: https://arxiv.org/abs/2511.21689

Paper: https://arxiv.org/abs/2511.21689v1

Register: https://www.AiFeta.com

AI MachineLearning LLM Tools ReinforcementLearning Efficiency Research NLP

Read more

Beyond URLs: Metadata That Makes LLMs Train Faster

Beyond URLs: Metadata That Makes LLMs Train Faster

Smarter LLMs, Faster—thanks to metadata What if training a large language model didn't just rely on text, but on the context around it? This study shows that adding fine-grained metadata—not just URLs—can meaningfully speed up pretraining and improve quality. * Beyond URLs: detailed quality signals (e.

Escaping the Verifier: Learning to Reason via Demonstrations

Escaping the Verifier: Learning to Reason via Demonstrations

LLMs can learn to reason—without task verifiers Many real-world problems don’t have automatic checkers to grade answers, even though we have lots of expert solutions. RARO (Relativistic Adversarial Reasoning Optimization) shows how to train reasoning skills from those examples alone. How it works: * A policy (the model) tries

VacuumVLA: A Two-in-One Robot Hand That Grips and Suctions

VacuumVLA: A Two-in-One Robot Hand That Grips and Suctions

Robots guided by Vision-Language-Action (VLA) AI are getting better at everyday tasks—but most still use simple two-finger grippers. That limits them on smooth, flat, or handleless objects. VacuumVLA is a low-cost robot hand that merges a standard two-finger gripper with a vacuum suction cup. The robot can switch between

ChatDRex: No‑Code, Conversational AI for Drug Repurposing

ChatDRex: No‑Code, Conversational AI for Drug Repurposing

Meet ChatDRex Finding new uses for approved drugs can save years and millions. But making those predictions usually takes teams of specialists and a tangle of tools. ChatDRex changes that. It’s a conversation-based, no‑code, multi‑agent system that lets clinicians and researchers ask complex bioinformatics questions in plain