MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair

• URL: http://arxiv.org/abs/2508.06963v1
• Date: Sat, 09 Aug 2025 12:20:00 GMT
• Title: MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair
• Authors: Changqing Li, Tianlin Li, Xiaohan Zhang, Aishan Liu, Li Pan,
• Abstract summary: MASteer is an end-to-end framework for trustworthiness repair in Large Language Models (LLMs)<n>It integrates two core components: AutoTester, a multi-agent system that generates diverse, high-quality steer samples tailored to developer needs; and AutoRepairer, which constructs adaptive steering strategies with anchor vectors for automated, context-aware strategy selection during inference.<n>Experiments show MASteer consistently outperforms baselines, improving metrics by 15.36% on LLaMA-3.1-8B-Chat and 4.21% on Qwen-3-8B-Chat, while maintaining general model capabilities.
• Score: 24.187162194500317
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) face persistent and evolving trustworthiness issues, motivating developers to seek automated and flexible repair methods that enable convenient deployment across diverse scenarios. Existing repair methods like supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) are costly and slow, while prompt engineering lacks robustness and scalability. Representation engineering, which steers model behavior by injecting targeted concept vectors during inference, offers a lightweight, training-free alternative. However, current approaches depend on manually crafted samples and fixed steering strategies, limiting automation and adaptability. To overcome these challenges, we propose MASteer, the first end-to-end framework for trustworthiness repair in LLMs based on representation engineering. MASteer integrates two core components: AutoTester, a multi-agent system that generates diverse, high-quality steer samples tailored to developer needs; and AutoRepairer, which constructs adaptive steering strategies with anchor vectors for automated, context-aware strategy selection during inference. Experiments on standard and customized trustworthiness tasks show MASteer consistently outperforms baselines, improving metrics by 15.36% on LLaMA-3.1-8B-Chat and 4.21% on Qwen-3-8B-Chat, while maintaining general model capabilities. MASteer demonstrates strong robustness, generalization, and practical value for scalable, efficient trustworthiness repair.

Related papers

• GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning [54.42973725693]
  We introduce GenAgent, unifying visual understanding and generation through an agentic multimodal model.<n>GenAgent significantly boosts base generator(FLUX.1-dev) performance on GenEval++ and WISE.<n>Our framework demonstrates three key properties: 1) cross-tool generalization to generators with varying capabilities, 2) test-time scaling with consistent improvements across interaction rounds, and 3) task-adaptive reasoning that automatically adjusts to different tasks.
  arXiv  Detail & Related papers  (2026-01-26T14:49:04Z)
• Agentic Confidence Calibration [67.50096917021521]
  Holistic Trajectory (HTC) is a novel diagnostic framework for AI agents.<n>HTC consistently surpasses strong baselines in both calibration and discrimination.<n>HTC provides interpretability by revealing the signals behind failure.
  arXiv  Detail & Related papers  (2026-01-22T09:08:25Z)
• MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux [37.49192877577783]
  We present MagicGUI-RMS, a multi-agent reward model system that delivers adaptive trajectory evaluation, corrective feedback, and self-evolving learning capabilities.<n>To support reward learning at scale, we design a structured data construction pipeline that automatically produces balanced and diverse reward datasets.<n>Experiments demonstrate that MagicGUI-RMS yields substantial gains in task accuracy, behavioral robustness.
  arXiv  Detail & Related papers  (2026-01-19T13:50:43Z)
• Testing and Enhancing Multi-Agent Systems for Robust Code Generation [21.38351747327572]
  Multi-agent systems (MASs) have emerged as a promising paradigm for automated code generation.<n>Despite their prosperous development and adoption, their robustness remains pressingly under-explored.<n>This paper presents the first comprehensive study examining the robustness of MASs for code generation through a fuzzing-based testing approach.
  arXiv  Detail & Related papers  (2025-10-12T05:45:04Z)
• A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models [4.417707977122247]
  We propose AdaPO, an online reinforcement learning framework capable of adaptively adjusting training objective in real time.<n>We show that our method significantly enhances both direct reasoning and self-evaluation capability.
  arXiv  Detail & Related papers  (2025-08-05T07:54:01Z)
• Automating Steering for Safe Multimodal Large Language Models [58.36932318051907]
  We introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model.<n>AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected.
  arXiv  Detail & Related papers  (2025-07-17T16:04:55Z)
• MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision [76.42361936804313]
  We introduce MAS-ZERO, the first self-evolved, inference-time framework for automatic MAS design.<n> MAS-ZERO employs meta-level design to iteratively generate, evaluate, and refine MAS configurations tailored to each problem instance.
  arXiv  Detail & Related papers  (2025-05-21T00:56:09Z)
• SMART: Self-Aware Agent for Tool Overuse Mitigation [58.748554080273585]
  Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness.<n>This imbalance leads to Tool Overuse, where models unnecessarily rely on external tools for tasks with parametric knowledge.<n>We introduce SMART (Strategic Model-Aware Reasoning with Tools), a paradigm that enhances an agent's self-awareness to optimize task handling and reduce tool overuse.
  arXiv  Detail & Related papers  (2025-02-17T04:50:37Z)
• Transformer-Squared: Self-adaptive LLMs [29.1326358746118]
  We introduce Transformer-Squared, a novel self-adaptation framework that adapts large language models for unseen tasks in real-time.<n>Our method consistently outperforms ubiquitous approaches such as LoRA, with fewer parameters and greater efficiency.<n> Transformer-Squared represents a significant leap forward, offering a scalable, efficient solution for enhancing the adaptability and task-specific performance of LLMs.
  arXiv  Detail & Related papers  (2025-01-09T01:19:21Z)
• Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach [31.654345704242512]
  This paper introduces a novel, model-level judge-free self-improvement framework.<n>Our approach employs a controlled feedback mechanism while eliminating the need for MLLMs in the verification loop.<n>We achieve superior precision and recall with significantly lower computational demands.
  arXiv  Detail & Related papers  (2024-11-26T00:44:37Z)
• On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning [100.14809391594109]
  Model-agnostic meta-learning (MAML) has emerged as one of the most successful meta-learning techniques in few-shot learning. Despite the generalization power of the meta-model, it remains elusive that how adversarial robustness can be maintained by MAML in few-shot learning. We propose a general but easily-optimized robustness-regularized meta-learning framework, which allows the use of unlabeled data augmentation, fast adversarial attack generation, and computationally-light fine-tuning.
  arXiv  Detail & Related papers  (2021-02-20T22:03:04Z)
• UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers [108.92194081987967]
  We make the first attempt to explore a universal multi-agent reinforcement learning pipeline, designing one single architecture to fit tasks. Unlike previous RNN-based models, we utilize a transformer-based model to generate a flexible policy. The proposed model, named as Universal Policy Decoupling Transformer (UPDeT), further relaxes the action restriction and makes the multi-agent task's decision process more explainable.
  arXiv  Detail & Related papers  (2021-01-20T07:24:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.