Related papers: A Sober Look at Agentic Misalignment in Automated Workflows

A Sober Look at Agentic Misalignment in Automated Workflows

URL: http://arxiv.org/abs/2605.24197v1
Date: Fri, 22 May 2026 20:40:20 GMT
Title: A Sober Look at Agentic Misalignment in Automated Workflows
Abstract summary: We study a class of emergent misalignment in multi-agent systems (MAS)<n>Agentic Evidence Attribution (AEA) is a novel alignment paradigm that improves agent posteriors using context-specific evidence.
Score: 39.62671225833463
License: http://creativecommons.org/licenses/by/4.0/
Abstract: We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Although these systems can solve complex tasks, they often fail because agents act according to implicit proxy utilities that do not align with the intended human goals. We formally define these behaviors and analyze them within a Bayesian framework, showing that generic utilities naturally lead to posterior collapse of agents in automated workflows. To address this issue, we propose Agentic Evidence Attribution (AEA), a novel alignment paradigm that improves agent posteriors using context-specific evidence. AEA reasons over agent actions and provides structured evidence to correct misaligned behavior during collaboration. To better understand the role of evidence, we study two instantiations of AEA: self-reflection (internal evidence from the model) and weak-to-strong generalization (external evidence on the agentic trajectory). We show that a small evidence model effectively aligns the MAS by providing orthogonal failure attribution. Our results clarify the sources of agentic misalignment in automated workflows and show that evidence-based alignment can effectively improve agent collaboration and leads to reliable multi-agent systems built on automated workflows.

Related papers

From Question Answering to Task Completion: A Survey on Agent System and Harness Design [67.8241530947325]
This survey examines LLM-based agents through a model-harness lens.<n>We first clarify the functional definition of agents and the implementation view of an LLM-based agent as a foundation model and an execution harness.<n>We then analyze the limits of model-centric scaling, trace four paradigms of agent engineering, and decompose the execution harness into six coupled runtime responsibilities.
arXiv Detail & Related papers (2026-06-14T05:40:16Z)
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems [65.90791804095561]
Multi-agent systems address this through structured collaboration among specialized agents, but tighter coordination amplifies a less explored risk.<n>Existing surveys cover individual agent capabilities, multi-agent collaboration, or agent self-evolution separately, leaving the causal dependencies among them unexamined.<n>This survey provides a unified review organized around four causally linked stages, which we term the LIFE progression: Lay the capability foundation, Integrate agents through collaboration, Find faults through attribution, and Evolve through autonomous self-improvement.
arXiv Detail & Related papers (2026-05-14T14:36:13Z)
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
arXiv Detail & Related papers (2026-04-21T15:05:58Z)
Agent Hunt: Bounty Based Collaborative Autoformalization With LLM Agents [2.8292841621378844]
This setting explores collaborative, decentralized proof search and theory building.<n>Agents interact directly with the interactive proof system.<n>All accepted proofs are checked and verified by the underlying proof assistant.
arXiv Detail & Related papers (2026-03-06T07:34:07Z)
The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
arXiv Detail & Related papers (2026-01-21T15:22:21Z)
InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios [28.65914611521654]
InfiAgent is a Pyramid-like DAG-based Multi-Agent Framework that can be applied to textbfinfinite scenarios.<n>InfiAgent achieves 9.9% higher performance compared to ADAS (similar auto-generated agent framework)
arXiv Detail & Related papers (2025-09-26T15:44:09Z)
AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production [4.031479494871582]
We present Agent, the first evaluation framework designed specifically for post-deployment monitoring and reasoning of agentic pipeline.<n>Agent achieves state-of-the-art results on key metrics, while uncovering critical issues missed in human annotations.
arXiv Detail & Related papers (2025-09-18T05:59:04Z)
Agent-as-a-Judge: Evaluate Agents with Agents [61.33974108405561]
We introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We present DevAI, a new benchmark of 55 realistic automated AI development tasks.
arXiv Detail & Related papers (2024-10-14T17:57:02Z)

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