Agent-as-a-Judge

Kari Jaaskelainen

10 Jan 2026 — 1 min read

Agent-as-a-Judge: the next step in trustworthy AI evaluation

As AI tasks get more complex, one-shot model graders fall short—biased, shallow, and unable to check the real world. This new survey traces the shift from LLM-as-a-Judge to agentic judges that plan, use tools, collaborate, and remember—making evaluations more robust and verifiable.

A unified framework and developmental taxonomy
Core methods: planning, tool-augmented verification, multi-agent debate, persistent memory
Applications across general and professional domains
Frontier challenges and a research roadmap

The goal: evaluations you can trust, not just outputs you can read.

Paper by Runyang You, Hongru Cai, Caiqi Zhang, Qiancheng Xu, Meng Liu, Tiezheng Yu, Yongqi Li, Wenjie Li (cs.CL, cs.AI). Read: https://arxiv.org/abs/2601.05111v1

Paper: https://arxiv.org/abs/2601.05111v1

Register: https://www.AiFeta.com

#AI #LLM #Agents #AgenticAI #Evaluation #NLP #MachineLearning #AIEthics #Benchmarks #Research

Read more

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

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

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

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

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