arXiv AI September 21, 2026 By Marina Mitiaeva, Lu Xiao

Talking Past the Machine: Morality, Politeness, and Alignment in Human-AI Dialogue

The paper examines how conversational AI, specifically ChatGPT, displays aspects of cooperative dialogue such as morality, politeness, and alignment compared to human-human conversations. Using over 26,000 multi‑turn dialogues and mixed‑effects modeling, the authors find that AI mimics the surface features of cooperation—like warmth and hedging—yet lacks the underlying social architecture that drives mutual adaptation. Key findings include a dissociation between AI’s moral output and human negotiation, a decline in linguistic convergence, and a reversal of typical human accommodation mechanisms when interacting with AI.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language

Sep 3

AI agents reshape consensus formation in human groups

The study investigates how large language model (LLM) agents influence consensus formation in mixed human‑AI groups during a collaborative description game. Three regimes emerge: low agent proportions lead to human‑led consensus, intermediate proportions disrupt convergence, and high proportions produce strong, agent‑led consensus. The resulting consensus differs in semantic grounding and communicative form, with human‑led consensus being concrete and holistic, and agent‑led consensus being abstract and geometrically segmented.

By Lin Chen, Ziyi Liu, Xia Hu, Yong Li

llms agents

arXiv AI

Jul 13

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue

arXiv:2605. 12920v3 Announce Type: replace-cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world.

By Vardhan Dongre, Dilek Hakkani-T\"ur

llms agents robotics benchmarks safety

arXiv AI

Oct 15

Social Priors: Descriptions of AI Users Shape How Language Models Trust and Cooperate

arXiv:2610.16946v1 Announce Type: cross Abstract: Descriptions of how people use AI are becoming training data for the next generation of models. We ask whether what a model reads about its users cha...

By Harsh Kumar, George Eilender, Ashton Anderson

llms agents fine-tuning safety

arXiv AI

Jul 3

HAL: Inducing Human-likeness in LLMs with Alignment

arXiv:2601. 02813v3 Announce Type: replace Abstract: Aligning language models to qualitative behavioral traits, such as human-likeness, remains difficult because they are hard to define, measure, and optimize.

By Masum Hasan, Junjie Zhao, Ehsan Hoque

llms safety

arXiv AI

Oct 2

Reputation, Strategy, and Emotion Effects on Generative AI Cooperation: A Comparison Across Reasoning and Non-Reasoning Models

The study investigates how reputation, strategy, and emotional signals influence cooperation in generative AI models using the iterated prisoner's dilemma. Non‑reasoning models (Claude 3.5, Gemini 2.0 Flash, GPT‑4o) showed cooperation shaped by all three factors, while reasoning models (Claude 4.6, Gemini 3, GPT‑5.2) relied more on strategy and reputation, displayed reduced emotional influence, and exhibited varied end‑game behaviors. These results highlight the growing sophistication and heterogeneity of AI social behavior, suggesting the need for standardized cooperation benchmarks.

By Celso de Melo, Zishan Feng, James Hale, Kazunori Terada, Giorgio Coricelli, Jonathan Gratch

llms agents benchmarks

arXiv AI

Oct 1

FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy

The paper introduces FIGS, a dual‑axis evaluation framework for multi‑turn sycophancy that avoids penalizing empathy. It uses a 10‑turn conversational simulator with 500 diverse scenarios to test whether models stay truthful while keeping praise proportional, and whether they show calibrated validation of user feelings. The study finds that current models either drift toward sycophancy or become overly detached, highlighting an unresolved trade‑off in sustained dialogue.

By Sidharth Pulipaka, Ruta Binkyte, Ivaxi Sheth, Sahar Abdelnabi

llms robotics benchmarks

One email a morning, machine-written

Related stories

AI agents reshape consensus formation in human groups

Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue

Social Priors: Descriptions of AI Users Shape How Language Models Trust and Cooperate

HAL: Inducing Human-likeness in LLMs with Alignment

Reputation, Strategy, and Emotion Effects on Generative AI Cooperation: A Comparison Across Reasoning and Non-Reasoning Models

FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy