Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict

Hugging Face Daily Papers Papers
llm-agents epistemic-humility knowledge-conflict evaluation uncertainty trajectory-analysis

Summary

该论文提出以“认知谦逊”（Epistemic Humility）评估 LLM 智能体在知识冲突下的表现，通过 Identify、Solve、Escalate 三个轨迹级维度进行衡量，发现高任务准确率并不意味着更高的认知谦逊，且模型级干预往往以牺牲准确率为代价。

When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or persist with an incorrect conclusion? Existing evaluations of agentic systems focus primarily on task success, offering limited insight into how agents handle such conflicts. We propose to evaluate agents on epistemic humility (EH): the agent's willingness to recognize, act on, and communicate uncertainty during task execution. We operationalize EH through three trajectory-level behavioral dimensions: Identify, Solve, and Escalate (ISE). Through knowledge conflict, situations where the backbone language model's parametric knowledge contradicts the evidence it encounters, or where two contextual sources disagree, we evaluate two conflict settings: (1) controlled conflict and (2) naturally occurring conflict during multi-step agentic execution, each paired with matched no-conflict controls. Evaluating four agents, we find that higher task accuracy does not necessarily correspond to greater epistemic humility: some high-accuracy configurations recognize conflicts during execution but do not communicate unresolved uncertainty in their incorrect final answers. Trajectory-level analysis further reveals that agents frequently detect conflicts in early steps of execution but fail to maintain or resolve them in later steps. Finally, we show that model-level interventions can improve EH, but often at the cost of task accuracy, suggesting that epistemic humility emerges from the interaction among the backbone model, agent harness, and evaluation environment.
Original Article
View Cached Full Text

Cached at: 10/09/26, 06:20 AM

Paper page - Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict

Source: https://huggingface.co/papers/2610.12360

Abstract

Whenretrievedevidencecontradictsanagent’spriorbeliefs,doesitreviseitsanswer,acknowledgeuncertainty,orpersistwithanincorrectconclusion?Existingevaluationsofagenticsystemsfocusprimarilyontasksuccess,offeringlimitedinsightintohowagentshandlesuchconflicts.Weproposetoevaluateagentsonepistemichumility(EH):theagent’swillingnesstorecognize,acton,andcommunicateuncertaintyduringtaskexecution.WeoperationalizeEHthroughthreetrajectory-levelbehavioraldimensions:Identify,Solve,andEscalate(ISE).Throughknowledgeconflict,situationswherethebackbonelanguagemodel’sparametricknowledgecontradictstheevidenceitencounters,orwheretwocontextualsourcesdisagree,weevaluatetwoconflictsettings:(1)controlledconflictand(2)naturallyoccurringconflictduringmulti-stepagenticexecution,eachpairedwithmatchedno-conflictcontrols.Evaluatingfouragents,wefindthathighertaskaccuracydoesnotnecessarilycorrespondtogreaterepistemichumility:somehigh-accuracyconfigurationsrecognizeconflictsduringexecutionbutdonotcommunicateunresolveduncertaintyintheirincorrectfinalanswers.Trajectory-levelanalysisfurtherrevealsthatagentsfrequentlydetectconflictsinearlystepsofexecutionbutfailtomaintainorresolvetheminlatersteps.Finally,weshowthatmodel-levelinterventionscanimproveEH,butoftenatthecostoftaskaccuracy,suggestingthatepistemichumilityemergesfromtheinteractionamongthebackbonemodel,agentharness,andevaluationenvironment.

View arXiv pageView PDFGitHub1Add to collection

Get this paper in your agent:

hf papers read 2610\.12360

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.12360 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.12360 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.12360 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Competence-Aware Orchestration for LLM-Based Multi-Agent Systems

arXiv cs.AI

该论文提出了一种两阶段的 competence-aware 框架，用于 LLM 多智能体系统的自动编排，根据模型在当前查询上的能力动态调整角色激活与通信图，在六个基准上平均达到 93.81%，同时在高能力骨干上降低 36.26% 的 token 成本。