# Paper: Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents

---
type: paper
title: Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
authors: Yuxin Liu, Mingye Zhu, Siyuan Liu, Bo Hu, Lei Zhang
year: 2026
venue: arXiv
url: https://arxiv.org/abs/2603.01438
code_url:
source: arxiv
collected_at: 2026-07-08
published_at: 2026-03-02
updated_at: 2026-03-02
status: queued
relevance: high
topics:
  - agent-safety
  - coding-agent
  - computer-use
  - planning
  - rag
  - world-model
methods:
  -
benchmarks:
  -
models:
  -
datasets:
  - cs.CL
  - cs.AI
related_concepts:
  -
related_jobs:
  -
related_experiments:
  -
related_projects:
  -
collection_score: 14
collection_queries: language-agent
---

## One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

## Why Collected

- matched queries: language-agent
- inferred topics: agent-safety, coding-agent, computer-use, planning, rag, world-model
- arXiv categories: cs.CL, cs.AI
- collection score: 14

## Review Checklist

- Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
- Does it include a benchmark, dataset, code, or reproducible experimental setup?
- Should it be promoted from `queued` to `skimmed` or `summarized`?

## Links

- arXiv: https://arxiv.org/abs/2603.01438