# Gavel: Agent Meets Checklist for Evaluating LLMs on Long-Context Legal Summarization

arXiv: https://arxiv.org/abs/2601.04424 · HTML: https://mlsanity.com/paper/2601.04424/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 62 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 24 of 24)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild](https://mlsanity.com/paper/2406.04770/) (2024)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [BooookScore: A systematic exploration of book-length summarization in the era of LLMs](https://mlsanity.com/paper/2310.00785/) (2023)
- [Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading](https://mlsanity.com/paper/2310.05029/) (2023)
- [HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2410.02694/) (2024)
- [WiCE: Real-World Entailment for Claims in Wikipedia](https://mlsanity.com/paper/2303.01432/) (2023)
- [Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution](https://mlsanity.com/paper/2505.20286/) (2025)
- [TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation](https://mlsanity.com/paper/2410.03608/) (2024)
- [PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents](https://mlsanity.com/paper/2305.14564/) (2023)
- [Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?](https://mlsanity.com/paper/2411.02400/) (2024)
- [FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction](https://mlsanity.com/paper/2403.02270/) (2024)
- [ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining](https://mlsanity.com/paper/2209.01650/) (2022)
- [FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence](https://mlsanity.com/paper/2402.11456/) (2024)
- [Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?](https://mlsanity.com/paper/2508.15218/) (2025)
- [Thresh: A Unified, Customizable and Deployable Platform for Fine-Grained Text Evaluation](https://mlsanity.com/paper/2308.06953/) (2023)
- [CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions](https://mlsanity.com/paper/2501.00097/) (2024)

## Abstract (arXiv)

Large language models (LLMs) now support contexts of up to 1M tokens, but their strengths and weaknesses on complex long-context tasks remain unclear. To study this, we focus on multi-document legal case summarization, where a single case often spans many documents exceeding 100K tokens. We systematically evaluate 12 frontier LLMs with Gavel, which consists of Gavel-Ref, a reference-based evaluation framework with checklist, residual-fact, and writing-style evaluations, and Gavel-Agent, a reference-free agent for evaluating factual coverage directly from source documents. Our results show that current models are more prone to omitting key information than hallucinating. They all perform well on simple checklist items, such as filing date, but struggle with rare and complex items, such as settlements. Performance also declines as case length increases. To meta-evaluate Gavel, we collect 160 hours of human annotations. Gavel-Agent reduces token usage by at least 36% compared to end-to-end and chunk-by-chunk methods while achieving competitive performance. Gavel-Agent also generalizes to the medical domain, performing the best with at least 77% fewer tokens.