Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ben-Gigi, Roi, David, Yuval, Fournier, Fabiana, Limonad, Lior, Moshkovich, Dany, Mulian, Hadar, Shlomov, Segev
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915933396664320
author Ben-Gigi, Roi
David, Yuval
Fournier, Fabiana
Limonad, Lior
Moshkovich, Dany
Mulian, Hadar
Shlomov, Segev
author_facet Ben-Gigi, Roi
David, Yuval
Fournier, Fabiana
Limonad, Lior
Moshkovich, Dany
Mulian, Hadar
Shlomov, Segev
contents AI agent development relies heavily on natural language prompting to define agents' tasks, knowledge, and goals. These prompts are interpreted by Large Language Models (LLMs), which govern agent behavior. Consequently, agentic performance is susceptible to variability arising from imprecise or ambiguous prompt formulations. Identifying and correcting such issues requires examining not only the agent's code, but also the internal system prompts generated throughout its execution lifecycle, as reflected in execution logs. In this work, we introduce an analytics pipeline implemented as part of the Agent Mentor open-source library that monitors and incrementally adapts the system prompts defining another agent's behavior. The pipeline improves performance by systematically injecting corrective instructions into the agent's knowledge. We describe its underlying mechanism, with particular emphasis on identifying semantic features associated with undesired behaviors and using them to derive corrective statements. We evaluate the proposed pipeline across three exemplar agent configurations and benchmark tasks using repeated execution runs to assess effectiveness. These experiments provide an initial exploration of automating such a mentoring pipeline within future agentic governance frameworks. Overall, the approach demonstrates consistent and measurable accuracy improvements across diverse configurations, particularly in settings dominated by specification ambiguity. For reproducibility, we released our code as open source under the Agent Mentor library.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10513
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis
Ben-Gigi, Roi
David, Yuval
Fournier, Fabiana
Limonad, Lior
Moshkovich, Dany
Mulian, Hadar
Shlomov, Segev
Artificial Intelligence
AI agent development relies heavily on natural language prompting to define agents' tasks, knowledge, and goals. These prompts are interpreted by Large Language Models (LLMs), which govern agent behavior. Consequently, agentic performance is susceptible to variability arising from imprecise or ambiguous prompt formulations. Identifying and correcting such issues requires examining not only the agent's code, but also the internal system prompts generated throughout its execution lifecycle, as reflected in execution logs. In this work, we introduce an analytics pipeline implemented as part of the Agent Mentor open-source library that monitors and incrementally adapts the system prompts defining another agent's behavior. The pipeline improves performance by systematically injecting corrective instructions into the agent's knowledge. We describe its underlying mechanism, with particular emphasis on identifying semantic features associated with undesired behaviors and using them to derive corrective statements. We evaluate the proposed pipeline across three exemplar agent configurations and benchmark tasks using repeated execution runs to assess effectiveness. These experiments provide an initial exploration of automating such a mentoring pipeline within future agentic governance frameworks. Overall, the approach demonstrates consistent and measurable accuracy improvements across diverse configurations, particularly in settings dominated by specification ambiguity. For reproducibility, we released our code as open source under the Agent Mentor library.
title Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis
topic Artificial Intelligence
url https://arxiv.org/abs/2604.10513