Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment — Paper

Abstract

Agentic large language model (LLM) systems are reshaping scientific workflows in chemistry and drug discovery, but evaluating their open-ended, tool-augmented outputs remains a fundamental bottleneck. The LLM-as-a-Judge paradigm has emerged as a scalable alternative, but existing drug discovery benchmarks deploy LLM judges without validating their alignment with human experts. In this work, we present an LLM-as-a-Judge evaluation framework for ChatInvent, an agentic drug discovery assistant deployed at AstraZeneca, with five contributions. First, we define four output-quality evaluation dimensions---Completeness, Relevancy, Structural Clarity, and Scope Adherence---alongside deterministic Tool Call Correctness checks. Second, we validate the judge through a human alignment study with five expert annotators, comparing Gemini 3.1 Pro, Claude Opus 4.7, GPT-5, and Llama 3.1 70B as candidate judges. Third, we optimize the best-performing judge using few-shot demonstrations of human-annotated examples, improving alignment with the human majority vote from 0.80 to 0.86. Fourth, applying the optimized judge to 70 held-out questions, we surface concrete limitations and find no strong evidence that informal phrasing degrades output quality; it may, however, still be helpful to have the LLM rewrite the original question before querying the agent. Finally, we extend the framework to 38 adversarial questions that are ambiguous, invalid, out-of-scope or ethically sensitive, and show that the agent's refusal behavior is guided by the stated intent of a request. Our framework provides a reusable template for human-aligned evaluation of agentic systems in scientific domains.

Authors 3

Emma Granqvist, Roc\'io Mercado, Samuel Genheden

Specification

Official page: arxiv.org/abs/2608.21057
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Arxiv announce type: replace
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
arXiv id: 2608.21057
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Categories: cs.LG
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
PDF: arxiv.org/pdf/2608.21057
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Primary category: cs.LG
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

7 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Emma Granqvist, Roc\'io Mercado, Samuel Genheden

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Authors

1 claims · 1 propertiesShow all properties

Authorsauthors1

Claim history for Authors
Value	Valid from → to	Status	Source	Confidence	Extractor
Emma Granqvist, Roc\'io Mercado, Samuel Genheden	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New paperPaperDesigning a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment
New paper: Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.LG	feed	T1· Official	5 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.