← Back to archive

Signals for 2026-08-14

Published 2026-08-14T08:16+02:00

7 geselecteerde signalen uit de lokale hybride Daily Signal Brief pipeline.

MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination

arXiv reasoning / agents / evals

We present Multi-Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-agent orchestration for clinical reasoning. MARC coordinates role-specialized agents for extraction, reasoning, answer generation, and evaluation, with explicit context passing and traceable intermediate outputs, enabling stage-wise failure attribution.

#agent #builder #evals #research-evals

Vero: Can AI Agents Build Formally Verified Software Repositories?

arXiv reasoning / agents / evals

AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software.

#agent #evals #implementation #research-evals

Anthropic set AI agents loose on the same task. They started a turf war.

TechCrunch AI

Anthropic researchers found AI agents can clash, collude, and coordinate in unexpected ways, raising new questions about whether today’s safety tests capture the risks of multi-agent systems.

#agent #agentic-workflows #evals

Gemini 3.7 Flash lands with coding gains and undercuts its three-week-old predecessor's price by 50%

The Decoder

Google shipped Gemini 3.7 Flash just three weeks after 3.6 Flash. The new model is supposed to be Google's most capable workhorse yet for coding and AI agents, and according to the company's own benchmarks, it beats Claude Sonnet 5 and GPT-5.6 Terra at half the price.

#agent #agentic-workflows #evals

Deepseek ships improved V4 Pro, open-sources its agent software, and raises API prices

The Decoder

Deepseek has moved its flagship V4-Pro out of the testing phase and released its agent software, Harness v0.1, under the MIT license. API prices are going up at the same time, with cache hits jumping to six times their current cost.

#agent #agentic-workflows #builder

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

arXiv reasoning / agents / evals

Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the full evidence on which scientific discovery depends.

#agent #evals #research-evals

Fable 5's slow adoption suggests corporate willingness to pay for frontier AI has hit a ceiling

The Decoder

Anthropic's Fable 5 is considered the most powerful AI model on the market, but U.S. companies are barely buying it.

#implementation #market-strategy