Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline
Quick Answer
This paper shows that An automated mediator using a structured LLM pipeline achieves comparable pre-mediation outcomes to human mediators, with 36% lower error in preference inference.
Quick Take
The system supports scalable, low-effort preparation for integrative negotiations, enhancing trust and confidence in agreements.
Key Points
- Automated mediator utilizes a structured pipeline for pre-mediation.
- Achieves 36% lower RMSE in preference inference compared to human mediators.
- Reduces excessive affirmation patterns from 36.6% to 16.8% with targeted prompt refinements.
- Supports scalable pre-mediation across all parties in a dispute.
- Comparable short-term outcomes in trust and confidence with human mediators.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 11379v1 Announce Type: new Abstract: Pre-mediation, the preparatory phase preceding direct human negotiation, plays a critical role in achieving mutually beneficial agreements, yet is often omitted due to cost, time, and limited access to trained mediators. We introduce an automated mediator for human negotiation, implemented as a structured pipeline of modules, that supports pre-mediation in integrative negotiation settings.
The pipeline decomposes preparation into specialized modules for dialogue, preference prediction, response-level critique, and structured summarization, separating inference, generation, and evaluation to address limitations of monolithic single-prompt approaches. We use the term "agent" for each module following common LLM-systems terminology, but the components are not autonomous and do not interact peer-to-peer; outputs are passed forward in a fixed sequence.
We evaluate the system in two controlled human-subject experiments comparing AI-based pre-mediation with professional human mediators in a multi-issue negotiation scenario. On short-term self-reported measures, the automated mediator achieves preparation outcomes broadly comparable to human mediators, including trust in the mediator and confidence in reaching mutually beneficial agreements, while achieving substantially lower error on the preference-inference task under our scenario and prompts (36% lower RMSE).
A second study shows that targeted prompt refinements reduce excessive affirmation patterns from 36. 6% to 16. 8%, matching human mediator baselines. Our findings suggest that structured LLM pipelines can provide scalable, low-effort pre-mediation support broadly comparable to human mediators on short-term self-reported preparation outcomes. The pipeline's single-party design mirrors how human mediators run pre-mediation today and enables parallel deployment across all parties to a dispute, supporting scalability.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.