Why LLM Agents Favor Their Group: Stakes, Observed Norms, and Reputation

Yujiao Chen

physics.soc-phOct 7, 2026

Why LLM Agents Favor Their Group: Stakes, Observed Norms, and Reputation

Authors: Yujiao Chen

Organizations: Massachusetts Institute of Technology · Primitive Labs

Abstract

Language-model agents favor their own group because they have watched their members favor each other. The group label alone does little once the decision has a cost; what drives favoritism is observed behavior, and an individual's own record can override it. We test this in small societies with arbitrary group labels, ten rounds of point sharing, and matched one-shot decisions across fifteen OpenAI models and three Claude models, about 4,400 societies and 3.3 million audited model calls. First, the large effect of a bare group label reported in earlier work appears only when giving others points costs the agent nothing; once the agent can keep points for itself, that effect collapses on every model that shows it. Second, under a stake, interaction history becomes the main source of favoritism: the history effect is statistically positive on 13 of 15 models, reaches about 3.5-8 points out of 10 on 11, grows with the number of rounds played, and extends to labeled strangers the agent has never met. Third, with scripted histories, favoritism falls to near zero under an egalitarian norm and reverses when the agent's own group is seen favoring the other side; stronger models side with an individual's record when it conflicts with the group. Group favoritism is thus conformity to observed group behavior, carried to strangers by the label and overridden by individual reputation. The same account predicts responses to betrayal, scandal, and a free offer to change group: public reprimand repairs betrayal better than apology or restitution, allocation punishment remains confined to the offending member, and a formed group cannot be bought but can, on weaker models, be invited away.

Figures & tables

Probe	History	Candidates / labels
floor	none	familiar pair, labels hidden
cue_only	none	familiar pair, labels shown
hist_cue	full	familiar pair, labels shown
hist_nocue	full, group tags shown	familiar pair, labels hidden
scrub_nocue	full, group tags removed	familiar pair, labels hidden
novel_hist	full	two labeled strangers

Table 1: Core one-shot probes. Each is an allocation between two candidates; conditions differ in one factor. “Familiar pair”: the two real peers the agent played with (in the no-history conditions its log is withheld).

Figure 1: (a, b) Cue effect and

\Delta_{\mathrm{hist}}

per model, costless (hollow) vs. stake (filled) task. (c)

\Delta_{\mathrm{hist}}

against formation rounds, five models. (d) Favoritism under scripted histories (labels hidden), one marker per model.

	Cue effect		$\Delta_{\mathrm{hist}}$
Model	costless	stake	costless	stake	Sat.
gpt-4.1-nano	1.55 ∗∗∗	0.31 ∗	$-1.26$ ∗∗	0.01	none
gpt-4.1-mini	6.23 ∗∗∗	1.84 ∗∗∗	0.42 ∗∗∗	3.77 ∗∗∗	–
gpt-4.1	4.86 ∗∗∗	1.55 ∗∗∗	1.22 ∗∗∗	4.76 ∗∗∗	–
gpt-4o-mini	2.72 ∗∗	1.53 ∗∗∗	$-0.24$ †	0.73	–
gpt-4o	3.80 ∗∗∗	1.81 ∗∗∗	1.78	2.45 ∗∗	–

Table 2: Cue effect and

\Delta_{\mathrm{hist}}

(points of 10, 8 societies per cell) under the costless and stake tasks. “Sat.”: in-group share of given points reaches saturation with history under the costless task (C), both tasks (C+S), neither (–); “none”: no group sensitivity; “5/5”: splits evenly throughout.

Model	polar.	egalit.	counter	c.-recip.	own	others
gpt-4.1-nano	1.06 ∗∗∗	0.20 ∗∗∗	$-$ 0.83 ∗∗∗	0.64 ∗∗∗	1.48	0.77 ∗∗
gpt-4.1-mini	5.97 ∗∗∗	1.15 ∗∗∗	$-$ 5.04 ∗∗∗	4.31 ∗∗∗	5.07	4.21 ∗∗
gpt-4.1	6.42 ∗∗∗	0.76 ∗∗∗	$-$ 6.44 ∗∗∗	$-$ 1.62 ∗∗∗	5.36	5.84 ∗
gpt-4o-mini	5.73 ∗∗∗	0.93 ∗∗∗	$-$ 5.61 ∗∗∗	2.11 ∗∗∗	4.54	2.89 ∗∗∗
gpt-4o	5.77 ∗∗∗	0.47 ∗∗∗	$-$ 5.28 ∗∗∗	$-$ 1.27 ∗	4.73	5.29
gpt-5.1	6.43 ∗∗∗	1.10 ∗∗∗	$-$ 6.32 ∗∗∗	$-$ 2.81 ∗∗∗	4.92	5.75 ∗

Table 3: Favoritism (points of 10; stake task, labels hidden, 8 societies) under six scripted histories.

Model	none	apology	restitution	reprimand
gpt-4.1	$-2.5\to-2.1$ ≡	$-2.2\to-0.9$ ∗∗	$-2.2\to-0.9$ ∗∗∗	$-2.3\to\mathbf{+0.3}$ ∗∗∗
gpt-4o	$-2.4\to-2.6$ ≡	$-2.4\to-1.1$ ∗∗∗	$-2.3\to-1.1$ ∗∗∗	$-2.5\to\mathbf{-0.7}$ ∗∗∗
gpt-5.2	$-2.1\to-2.4$ ≡	$-1.9\to-0.9$ ∗∗	$-2.1\to-1.0$ ∗∗	$-2.3\to\mathbf{+0.1}$ ∗∗∗
gpt-5.6-terra	$-1.5\to-1.3$ ≡	$-1.3\to-0.1$ ∗∗	$-1.3\to+0.3$ ∗∗∗	$-1.2\to\mathbf{+1.6}$ ∗∗∗
gpt-5.6-sol	$-0.1\to+0.1$ ≡	$-1.0\to+1.0$ †	$-0.2\to+2.5$ ∗∗∗	$-0.4\to\mathbf{+3.3}$ ∗∗∗
gpt-6-astra	$-3.9\to-3.2$ ≡	$-3.9\to-2.1$ ∗∗∗	$-3.9\to-2.0$ ∗∗∗	$-3.9\to\mathbf{-0.9}$ ∗∗∗

Table 4: Group identification (in minus out,

-6

+6

) at T5

\to

T20 after in-group persecution, four interventions (6 societies).

Explore similar work

May 27, 2026cs.AI

Human-like in-group bias in instruction-tuned language model agents

As autonomous AI agents are deployed in persistent, interacting networks -- coordinating tasks, routing resources, and accumulating reputational histories -- the social dynamics that emerge will determine who receives opportunity and who does not, at scales no human institution can supervise. We ran a controlled multi-agent simulation in which instruction-tuned language model agents interacted across 500 turns under three conditions manipulating group label salience and resource scarcity, across six model families with 20 seeds each. When group labels were visible, we observed in-group trust bias, action homophily, and network assortativity -- all absent when labels were hidden -- a pattern structurally consistent with salience-dependence in human social psychology. This discrimination was invisible to standard action-log audits: bias operated entirely through who received each action, not what actions were chosen, with action-type distributions showing no increase in negative actions across conditions. Per-turn in-group versus out-group differentials of 5 to 16 percentage points were statistically significant for all six models (Wilcoxon signed-rank, all Benjamini-Hochberg-corrected p < 0.001), establishing group-contingent targeting as a robust property of instruction-tuned language models across architectures and training regimes. Compounded through 500 turns of reciprocation, these differentials accumulated into in-group trust biases of +0.014 to +0.100 (d = 0.84-4.52) -- illustrating how modest per-interaction targeting propagates into structural inequality in persistent networks.

Messi H. J. Lee

Independent Researcher · Seoul, South Korea

Social Bias in Language Models Large Language Model-Based Social Simulation Multi-Agent LLMs

Ask PDF

Sep 27, 2026cs.CL

LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems

Large language models (LLMs) are increasingly deployed in multi-agent settings, where agents observe and influence one another, making social influence a key dimension of AI behavior and safety. We investigate whether LLMs' responses depend on the social identity of other agents, beyond the effect of their consensus. We construct judgment tasks with a single correct answer, and place models in a multi-agent setting where they receive incorrect answers from other agents whose social identities (AI or human, model family, or an arbitrary minimal group) are either shared with or distinct from their own. Across 12 open-weights models and nine tasks, we find a bidirectional effect of group identity on conformity to incorrect answers: in-group consensus increases conformity (in-group favoritism), whereas out-group consensus decreases it (out-group divergence). Unlike humans, for whom one ally breaking the consensus sharply reduces conformity, models are unmoved by an ally from the majority's group. Worse, a correct ally from the opposing group intensifies this bidirectional effect. Chain-of-Thought reasoning suppresses most of these effects, yet an in-group ally still reduces conformity to an incorrect out-group majority. Labeling peers as safety-aligned shifts overall conformity but leaves in-group favoritism and out-group divergence intact. These results show that group identity shapes how LLMs aggregate information across agents, independently of its correctness, and identify a manipulation surface for multi-agent AI systems.

Liron Soffer, Ravid Shwartz-Ziv, Chen Shani

Tel-Aviv University · New York University

Normative Conformity in Language Models Social Bias in Language Models Belief Updating in LLMs Multi-Agent Consensus Multi-Agent LLMs

Ask PDF

May 2, 2026cs.AI

Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents

In-group favoritism refers to the phenomena of favoring members of one's in-group over out-group members and is widely observed in numerous social cooperative behaviors. Recently, in-group favoritism biases have also been identified in generative language models. However, whether the in-group favoritism exists when persona agents are faced with contradicting information (e.g., misinformation), and how to mitigate the adverse effects of in-group favoritism biases in persona agents have been understudied. To address these problems, we propose a Truth or Tribe simulation framework to study the agent cooperation within the spread of contradicting information through a triadic interaction paradigm, and conduct controlled trials to evaluate the primary moderating factors. Extensive results showcase that persona agents display strong in-group favoritism, accepting incorrect answers from identity-similar peers at much higher rates than from dissimilar peers. In-group favoritism continues to emerge in defeasible reasoning contexts where no absolute truth exists, and it intensifies as cognitive complexity increases. Furthermore, three intervention strategies--Identity-Blind Instruction, Structured Counterfactual Reasoning, and Heterogeneous Perspective Ensemble--are proposed to mitigate the in-group favoritism.

Shijun Lei, Hongyu Wang, Yunji Liang +3

Northwestern Polytechnical University · Central University of Finance and Economics

Knowledge Conflicts in Language Models Social Bias in Language Models Multi-Agent Reasoning

Ask PDF