The study investigates whether large language models (LLMs) exhibit reward valuation mechanisms analogous to human anhedonia by applying clinical tests designed for major depressive disorder. Researchers identified reward‑anticipatory units in state‑of‑the‑art AI models, showed that perturbing these units predicts Nucleus Accumbens activity, and caused the models to choose low‑effort, low‑reward tasks—mirroring human anhedonia. The findings suggest that specific reward‑valuation circuits in AI can functionally resemble those in humans, providing a mechanistic bridge between computational and neurobiological models of motivation.
By Melika Honarmand, Samin Mahdipour Aghabagher, Martin Schrimpf
arXiv:2609.22090v1 Announce Type: new
Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Ps...
By Joy Bose
arXiv:2608. 05111v1 Announce Type: new Abstract: In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize their policies.
By Jai Malegaonkar, Rohan Patil, Henrik I. Christensen
arXiv:2606. 03238v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) makes large-scale post-training possible by replacing an underspecified human objective with learned and scalable proxies.
By Zelalem Abahana
arXiv:2607. 12823v1 Announce Type: new Abstract: Interaction with AI agents has become one of the most frequent activities of everyday digital life.
By Eranga Bandara, Ross Gore, Asanga Gunaratna, Ravi Mukkamala, Nihal Siriwardanagea, Gihan Siriwardanagea, Sachini Rajapakse, Isurunima Kularathna, Pramoda Karunarathna, Chalani Rajapakse, Sachin Shetty, Christopher K. Rhea, Ng Wee Keong, Kasun De Zoysa, Amin Hass, Shaifali Kaushik, Wathsala Herath, Preston Samuel, Anita H. Clayton, Atmaram Yarlagadd
arXiv:2606. 18963v1 Announce Type: new Abstract: We study online reward-punishment learning when the environment provides no scalar reward or evaluative label.
By Zirong Li
arXiv:2606. 15779v1 Announce Type: cross Abstract: Multimodal models can name the action units (AUs) behind a facial emotion, but their AU->emotion rationales are typically plausible rather than faithful: nothing forces the AUs a model invokes to be the AUs that actually drive its prediction.
By Van Thong Huynh, Hong Hai Nguyen, Thuy Pham, Trong Nghia Nguyen, Soo-Hyung Kim
arXiv:2607. 27224v1 Announce Type: cross Abstract: External and synthetic control arms (ECAs) are entering psychiatric drug development, but the field lacks a benchmark that evaluates the properties regulators care about: not only how accurately a method reconstructs untreated trajectories, but whether its uncertainty is calibrated, whether it is robust to the informative observation times common in mental-health records (sicker patients are seen more often), and what false-positive rate it induces in go/no-go trial decisions.
By Aakash Bhagat, Shashank Choudhary
arXiv:2606. 00860v1 Announce Type: cross Abstract: Self-report questionnaires remain the prevailing tool for probing the psychological states of persona-conditioned agents (PC-Agents).
By Ming Wang, Shuang Wu, Bixuan Wang, Lu Lin, Yuxin Chen, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang, Yufan Sun
arXiv:2606. 30068v1 Announce Type: new Abstract: Joint-embedding predictive (JEPA-style) objectives learn representations by predicting future latents.
By Ayan Pendharkar
arXiv:2607. 06626v1 Announce Type: new Abstract: Recent Vision-Language Models capture increasingly complex aspects of human cognition.
By Melika Honarmand, Samin Mahdipour Aghabagher, Martin Schrimpf
The paper introduces TRACE, a digital‑advertising diagnostic environment that uses simulated interventions to generate verifiable rewards for training reasoning agents. By injecting controlled interventions into a simulator, the hidden cause of anomalies becomes an oracle label, enabling agents to learn to identify root causes and affected segments through noisy, confounded evidence. Experiments show that reinforcement learning with these synthesized rewards outperforms large prompted baselines, achieving higher accuracy while using fewer tool calls.
By Rui Sun, Zhan Shi, Bing He