Cover Image

Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mujtaba, Dena, Hu, Brian, Hoogs, Anthony, Basharat, Arslan
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression
by: Adams, Jadie, et al.
Published: (2025)

ALIGN: Prompt-based Attribute Alignment for Reliable, Responsible, and Personalized LLM-based Decision-Making
by: Ravichandran, Bharadwaj, et al.
Published: (2025)

Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain
by: Hu, Brian, et al.
Published: (2024)

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
by: Zhang, Zhenyu, et al.
Published: (2025)

Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations
by: Zhu, Jian-Qiao, et al.
Published: (2025)

CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
by: Lv, Hang, et al.
Published: (2025)

Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games
by: Yadav, Neemesh, et al.
Published: (2025)

Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
by: Miyamoto, Sora, et al.
Published: (2026)

Test-Time Steering for Lossless Text Compression via Weighted Product of Experts
by: Zhang, Qihang, et al.
Published: (2025)

Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
by: Hu, Zhiyuan, et al.
Published: (2026)

Adaptive Decoding via Test-Time Policy Learning for Self-Improving Generation
by: Bhardwaj, Asmita, et al.
Published: (2026)

How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study
by: Sun, Moran, et al.
Published: (2026)

Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
by: Pres, Itamar, et al.
Published: (2024)

Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
by: Ye, Wengao, et al.
Published: (2025)

Agentic Test-Time Scaling for WebAgents
by: Lee, Nicholas, et al.
Published: (2026)

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
by: Li, Hao, et al.
Published: (2026)

Inference-time Alignment via Sparse Junction Steering
by: Hu, Runyi, et al.
Published: (2026)

Context Steering: Controllable Personalization at Inference Time
by: He, Jerry Zhi-Yang, et al.
Published: (2024)

Benchmark Test-Time Scaling of General LLM Agents
by: Li, Xiaochuan, et al.
Published: (2026)

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning
by: Wang, Yutong, et al.
Published: (2026)

Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection
by: Kumarage, Tharindu, et al.
Published: (2025)

Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies
by: Varshney, Prasoon, et al.
Published: (2025)

Aligning Large Language Model Behavior with Human Citation Preferences
by: Ando, Kenichiro, et al.
Published: (2026)

Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
by: Leong, Chak Tou, et al.
Published: (2026)

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
by: Chen, Yongchao, et al.
Published: (2025)

BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents
by: Ou, Litu, et al.
Published: (2025)

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
by: Wang, Jingxing, et al.
Published: (2026)

Program Synthesis via Test-Time Transduction
by: Lee, Kang-il, et al.
Published: (2025)

Agent-Testing Agent: A Meta-Agent for Automated Testing and Evaluation of Conversational AI Agents
by: Komoravolu, Sameer, et al.
Published: (2025)

The Real, the Better: Aligning Large Language Models with Online Human Behaviors
by: Jiang, Guanying, et al.
Published: (2024)

Steering Awareness: Detecting Activation Steering from Within
by: Rivera, Joshua Fonseca, et al.
Published: (2025)

HarmonyGuard: Toward Safety and Utility in Web Agents via Adaptive Policy Enhancement and Dual-Objective Optimization
by: Chen, Yurun, et al.
Published: (2025)

Sustainable Digitalization of Business with Multi-Agent RAG and LLM
by: Arslan, Muhammad, et al.
Published: (2025)

Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
by: Liu, Yuxin, et al.
Published: (2026)

DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping
by: Fan, Wei, et al.
Published: (2025)

TopoAlign: A Framework for Aligning Code to Math via Topological Decomposition
by: Li, Yupei, et al.
Published: (2025)

LLMs Reading the Rhythms of Daily Life: Aligned Understanding for Behavior Prediction and Generation
by: Meng, Fanjin, et al.
Published: (2026)

Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization
by: Zhang, Wenqi, et al.
Published: (2024)

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
by: Fang, Yi, et al.
Published: (2026)

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
by: Li, Hengli, et al.
Published: (2025)