paper-with-me

Papers

AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling

2026-08-27 · Abhigya Verma, Amit Kumar Saha, Seganrasan Subramanian, Sai Harshitha Aluru arxiv

LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely unexamined. We present AgentJudgeBench, the first benchmark to systematically study LLM-as-a-judge reliability for agentic tool-calling over workflow DAGs, as distinct from the broader LLM-as-a-judge task of open-ended text or preference evaluation. The benchmark comprises 3,808 instances spanning six DAG topologies and three difficulty tiers, evaluated with five generators (3B-70B open-weight models and GPT-5.4) and six judges (20B to frontier scale) under paired with- and without-ground-truth conditions. Judge alignment degrades monotonically with task difficulty, 1.5x faster without ground truth, and on hard queries without ground truth all six judges converge to a narrow 77-82% band regardless of scale, revealing a structural ceiling driven primarily by task difficulty, though its height is partly prompt-dependent for weaker generators, that model capacity alone cannot overcome. Ground-truth exposure is not uniformly beneficial: it reduces alignment for GPT-5.4 (1.5 pp) and Gemini-2.5-Pro (3.9 pp), consistent with over-anchoring. Among mitigation strategies, chain-of-thought reasoning and judge temperature both have negligible effect, while structured evaluation rubrics improve alignment by up to 6.5 pp but do not generalize uniformly across judge-generator pairs. With ground truth, QwQ-32B best matches the programmatic reference, while a human validation study identifies GPT-OSS-120B as the most human-aligned judge; without it, frontier judges lead only marginally within the shared ceiling. These results expose fundamental limitations of current LLM judges and yield practical guidelines for reliable evaluation in agentic systems.

📄 PDF Abstract BibTeX arXiv:2608.26623

Code (3)

Aaron617/agent-arXiv-daily ★ 9
Tavish9/awesome-daily-AI-arxiv ★ 113
grrlkk/writing-agent-arxiv-daily

Similar Papers 제목 키워드 기반

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges

2025-03-09 · Jiaxin Ai, Pengfei Zhou, Zhaopan Xu, Ming Li 외

As multi-modal large language models (MLLMs) frequently exhibit errors when solving scientific problems, evaluating the validity of their reasoning processes is critical for ensuring reliability and uncovering fine-grain…

JudgeBench: A Benchmark for Evaluating LLM-based Judges

2024-10-16 · Sijun Tan, Siyuan Zhuang, Kyle Montgomery, William Y. Tang 외

LLM-based judges have emerged as a scalable alternative to human evaluation and are increasingly used to assess, compare, and improve models. However, the reliability of LLM-based judges themselves is rarely scrutinized.…

Math

Tuning LLM Judges Hyperparameters

2025-01-24 · David Salinas, Omar Swelam, Frank Hutter

Evaluating Large Language Models (LLMs) often requires costly human annotations. To address this, LLM-based judges have been proposed, which compare the outputs of two LLMs enabling the ranking of models without human in…

SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues?

2026-01-07 · Jonggeun Lee, Junseong Pyo, Gyuhyeon Seo, Yohan Jo arxiv

Large Audio-Language Models (LALMs) as judges have emerged as a prominent approach for evaluating speech generation quality, yet their ability to assess speaker consistency across multi-turn dialogues remains unexplored.…

JudgeLM: Fine-tuned Large Language Models are Scalable Judges

2023-10-26 · Lianghui Zhu, Xinggang Wang, Xinlong Wang

Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalab…