#agent evaluation

try —

10 papers match

cs.CL2026

Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game

Niklas Bauer, Lars Benedikt Kaesberg, Akiko Aizawa +3

The paper introduces ParliamentBench, an open-source benchmark based on the Secret Hitler game, to evaluate large language model agents on deception, persuasion, and reasoning unde…

#large language models#deception#social deduction games#agent evaluation
cs.AI2026

Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation

Stefan Krsteski, Charlotte Meyer, Guillaume Allegre +2

The paper introduces Messier, a unified corpus of 957,253 standardized evaluation records spanning thousands of agents, tasks, and benchmarks, to enable cross‑benchmark analysis an…

#agent evaluation#benchmark consolidation#capability scaling#dataset infrastructure
cs.AI2026

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

Kai Chen, Zichen Ding, Jiaye Ge +22

The paper presents AgentCompass, an open‑source infrastructure that standardizes and simplifies the evaluation of large‑language‑model based autonomous agents by separating benchma…

#agent evaluation#large language models#benchmarking#software infrastructure
cs.SE2026

Copy-on-Write Scoring: Application-Specific Agent Evaluations

Joanna Roy, Sven Hoelzel

The paper presents Copy-on-Write (CoW) Scoring, a framework that uses PostgreSQL's copy‑on‑write mechanism to isolate and evaluate LLM‑based agents' database write operations withi…

#agent evaluation#copy-on-write#database testing#application-specific workflows
cs.AI2026

JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks

Lanbo Lin, Jiayao Liu, Tianyuan Yang +5

JADE is a two‑layer evaluation system that encodes expert knowledge as predefined evaluation skills and adds claim‑level, evidence‑gated assessment to more reliably evaluate AI age…

#agent evaluation#open-ended professional tasks#expert‑grounded assessment#dynamic claim-level evaluation
cs.AI2026

Rethinking the Evaluation of Harness Evolution for Agents

Yike Wang, Huaisheng Zhu, Zhengyu Hu +7

The paper reexamines how automatic harness evolution for large language model agents is evaluated, comparing it to simple test‑time scaling baselines and finding that it offers lim…

#large language models#agent evaluation#harness evolution#test-time scaling