# A Framework for Context Enrichment and Selective Robustness in LLM Social Agents

Source: [arXiv](https://arxiv.org/abs/2611.06914v1)  
Feed7 permalink: https://feed7.dev/p/2611-06914v1-1tz1eo5  
Published: 2026-11-04T18:58:23.000Z  
Trust: Needs Review (needs_review)

## Why Included

The paper tests whether richer prompts make simulated LLM agents less brittle. Its selective-robustness criterion may help builders distinguish useful context from wording that merely changes behavior.

## Source Summary

The framework compares four prompt enrichments: neutral padding, generic social background, descriptive grounding, and normative grounding. It defines selective robustness as resisting meaning-preserving prompt changes while responding directionally to relevant changes in the world. In a Prisoner’s Dilemma-like game, enrichment produced distinct behavior across **two models**.

## Practical Implication

When evaluating an agent, vary prompt wording separately from decision-relevant facts. Check that behavior stays stable under the first and changes appropriately under the second; adding background alone is not evidence of better grounding.

## Agent-Ready Context

The framework compares four prompt enrichments: neutral padding, generic social background, descriptive grounding, and normative grounding. It defines selective robustness as resisting meaning-preserving prompt changes while responding directionally to relevant changes in the world. In a Prisoner’s Dilemma-like game, enrichment produced distinct behavior across **two models**.

When evaluating an agent, vary prompt wording separately from decision-relevant facts. Check that behavior stays stable under the first and changes appropriately under the second; adding background alone is not evidence of better grounding.

The results are from a social simulation, and the paper says enrichment effects varied by model. The material does not establish which prompt type generalizes to coding agents or real tasks.

## Connected Context

Feed7 judgment across 1009 accumulated Signals:

This paper separates robustness to meaning-preserving prompt variation from responsiveness to relevant changes in the world, and tests the distinction in a social simulation with two models. It gives an evaluation principle for context behavior, but does not show that any enrichment method transfers to coding agents or real tasks.

- [Learning When to Trust via Selective Context Preference Optimization](https://feed7.dev/p/2608-06377v1-0rvbpra) — Both frame robustness as using relevant evidence while resisting misleading or irrelevant context; this paper adds a direct distinction between wording changes and decision-relevant world changes.
- [AISPA: User-Centric System Prompt Auditing for Large Language Model Applications](https://feed7.dev/p/2607-28617v1-1cbh1qu) — Both motivate behavioral evaluation of prompts rather than relying on prompt inspection alone; AISPA audits instruction properties, while this framework tests response stability and direction under controlled changes.

## Context Map

- Layer: context
- Domains: research
- Topics: context-engineering, prompting, agent-reliability

## Uncertainty

- The results are from a social simulation, and the paper says enrichment effects varied by model. The material does not establish which prompt type generalizes to coding agents or real tasks.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.