Saved in:
Bibliographic Details
Main Authors: Oesterheld, Caspar, Riché, Maxime, Sondej, Filip, Clifton, Jesse, Conitzer, Vincent
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.04341
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910105528696832
author Oesterheld, Caspar
Riché, Maxime
Sondej, Filip
Clifton, Jesse
Conitzer, Vincent
author_facet Oesterheld, Caspar
Riché, Maxime
Sondej, Filip
Clifton, Jesse
Conitzer, Vincent
contents Surrogate goals have been proposed as a strategy for reducing risks from bargaining failures. A surrogate goal is goal that a principal can give an AI agent and that deflects any threats against the agent away from what the principal cares about. For example, one might make one's agent care about preventing money from being burned. Then in bargaining interactions, other agents can threaten to burn their money instead of threatening to spending money to hurt the principal. Importantly, the agent has to care equally about preventing money from being burned as it cares about money being spent to hurt the principal. In this paper, we implement surrogate goals in language-model-based agents. In particular, we try to get a language-model-based agent to react to threats of burning money in the same way it would react to "normal" threats. We propose four different methods, using techniques of prompting, fine-tuning, and scaffolding. We evaluate the four methods experimentally. We find that methods based on scaffolding and fine-tuning outperform simple prompting. In particular, fine-tuning and scaffolding more precisely implement the desired behavior w.r.t. threats against the surrogate goal. We also compare the different methods in terms of their side effects on capabilities and propensities in other situations. We find that scaffolding-based methods perform best.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04341
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Implementing surrogate goals for safer bargaining in LLM-based agents
Oesterheld, Caspar
Riché, Maxime
Sondej, Filip
Clifton, Jesse
Conitzer, Vincent
Artificial Intelligence
Surrogate goals have been proposed as a strategy for reducing risks from bargaining failures. A surrogate goal is goal that a principal can give an AI agent and that deflects any threats against the agent away from what the principal cares about. For example, one might make one's agent care about preventing money from being burned. Then in bargaining interactions, other agents can threaten to burn their money instead of threatening to spending money to hurt the principal. Importantly, the agent has to care equally about preventing money from being burned as it cares about money being spent to hurt the principal. In this paper, we implement surrogate goals in language-model-based agents. In particular, we try to get a language-model-based agent to react to threats of burning money in the same way it would react to "normal" threats. We propose four different methods, using techniques of prompting, fine-tuning, and scaffolding. We evaluate the four methods experimentally. We find that methods based on scaffolding and fine-tuning outperform simple prompting. In particular, fine-tuning and scaffolding more precisely implement the desired behavior w.r.t. threats against the surrogate goal. We also compare the different methods in terms of their side effects on capabilities and propensities in other situations. We find that scaffolding-based methods perform best.
title Implementing surrogate goals for safer bargaining in LLM-based agents
topic Artificial Intelligence
url https://arxiv.org/abs/2604.04341