Saved in:
Bibliographic Details
Main Authors: Benac, Leo, Raedler, Jonas, Ma, Zilin, Doshi-Velez, Finale
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.14066
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910213528879104
author Benac, Leo
Raedler, Jonas
Ma, Zilin
Doshi-Velez, Finale
author_facet Benac, Leo
Raedler, Jonas
Ma, Zilin
Doshi-Velez, Finale
contents Many real-world multi-party negotiations unfold as sequences of binding, action-level commitments rather than a single final outcome, yet this regime remains under-studied in existing benchmarks. We introduce a benchmark and evaluation framework for this setting, combining a configurable negotiation game generator with document-grounded instances derived from a climate negotiation exercise. We also provide several baseline solvers. Exact evaluation on small games and comparative evaluation on larger instances show that no solver dominates across regimes; performance depends on the structural properties of the game. These results motivate the creation of novel negotiation methods that value partial commitments robustly across diverse strategic regimes. Code and data for the benchmark are available at: https://anonymous.4open.science/r/negotiation_MARL-46B8
format Preprint
id arxiv_https___arxiv_org_abs_2603_14066
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Benchmark for Multi-Party Negotiation Games from Real Negotiation Data
Benac, Leo
Raedler, Jonas
Ma, Zilin
Doshi-Velez, Finale
Multiagent Systems
Artificial Intelligence
Machine Learning
Many real-world multi-party negotiations unfold as sequences of binding, action-level commitments rather than a single final outcome, yet this regime remains under-studied in existing benchmarks. We introduce a benchmark and evaluation framework for this setting, combining a configurable negotiation game generator with document-grounded instances derived from a climate negotiation exercise. We also provide several baseline solvers. Exact evaluation on small games and comparative evaluation on larger instances show that no solver dominates across regimes; performance depends on the structural properties of the game. These results motivate the creation of novel negotiation methods that value partial commitments robustly across diverse strategic regimes. Code and data for the benchmark are available at: https://anonymous.4open.science/r/negotiation_MARL-46B8
title A Benchmark for Multi-Party Negotiation Games from Real Negotiation Data
topic Multiagent Systems
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.14066