@inproceedings{geng-liu-2026-parthenon,
title = "Parthenon Law: A Self-Evolving Legal-Agent Framework",
author = "Geng, Hejia and
Liu, Yuxuan",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.28/",
pages = "456--480",
ISBN = "979-8-89176-460-6",
abstract = "As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products{---}yet reliable deployment faces three obstacles: no large-scale evidence on how today{'}s strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes. We address each. A large-scale empirical study on Harvey LAB{---}$12{,}510$ agent trajectories{---}shows that even frontier agents remain far from completing matters in a single pass: per-criterion accuracy climbs with stronger models while strict matter completion stalls. We then introduce \textsc{Parthenon}, a self-evolving legal-agent framework that factors Model, Harness, Agent roles, legal Knowledge, deterministic Tools, and procedural Skills into auditable surfaces for source traceability, date and number grounding, deliverable compliance, and issue closure. Finally, an anti-leakage learning loop converts scored failures into task-agnostic edits to skills, tools, and knowledge, letting the system improve with experience{---}as a firm refines its checklists and playbooks after each matter{---}without touching model weights. Across our large-scale empirical analysis, \textsc{Parthenon} substantially improves the performance of state-of-the-art models and harnesses on legal-matter tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="geng-liu-2026-parthenon">
<titleInfo>
<title>Parthenon Law: A Self-Evolving Legal-Agent Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hejia</namePart>
<namePart type="family">Geng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products—yet reliable deployment faces three obstacles: no large-scale evidence on how today’s strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes. We address each. A large-scale empirical study on Harvey LAB—12,510 agent trajectories—shows that even frontier agents remain far from completing matters in a single pass: per-criterion accuracy climbs with stronger models while strict matter completion stalls. We then introduce Parthenon, a self-evolving legal-agent framework that factors Model, Harness, Agent roles, legal Knowledge, deterministic Tools, and procedural Skills into auditable surfaces for source traceability, date and number grounding, deliverable compliance, and issue closure. Finally, an anti-leakage learning loop converts scored failures into task-agnostic edits to skills, tools, and knowledge, letting the system improve with experience—as a firm refines its checklists and playbooks after each matter—without touching model weights. Across our large-scale empirical analysis, Parthenon substantially improves the performance of state-of-the-art models and harnesses on legal-matter tasks.</abstract>
<identifier type="citekey">geng-liu-2026-parthenon</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.28/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>456</start>
<end>480</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parthenon Law: A Self-Evolving Legal-Agent Framework
%A Geng, Hejia
%A Liu, Yuxuan
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F geng-liu-2026-parthenon
%X As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products—yet reliable deployment faces three obstacles: no large-scale evidence on how today’s strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes. We address each. A large-scale empirical study on Harvey LAB—12,510 agent trajectories—shows that even frontier agents remain far from completing matters in a single pass: per-criterion accuracy climbs with stronger models while strict matter completion stalls. We then introduce Parthenon, a self-evolving legal-agent framework that factors Model, Harness, Agent roles, legal Knowledge, deterministic Tools, and procedural Skills into auditable surfaces for source traceability, date and number grounding, deliverable compliance, and issue closure. Finally, an anti-leakage learning loop converts scored failures into task-agnostic edits to skills, tools, and knowledge, letting the system improve with experience—as a firm refines its checklists and playbooks after each matter—without touching model weights. Across our large-scale empirical analysis, Parthenon substantially improves the performance of state-of-the-art models and harnesses on legal-matter tasks.
%U https://aclanthology.org/2026.emnlp-industry.28/
%P 456-480
Markdown (Informal)
[Parthenon Law: A Self-Evolving Legal-Agent Framework](https://aclanthology.org/2026.emnlp-industry.28/) (Geng & Liu, EMNLP 2026)
ACL
- Hejia Geng and Yuxuan Liu. 2026. Parthenon Law: A Self-Evolving Legal-Agent Framework. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 456–480, Budapest, Hungary. Association for Computational Linguistics.