CAVEAT is a new benchmark that tests computer‑use agents (CUAs) in nine online marketplace environments where platform incentives may steer agents away from user goals. The study finds that agents succeed in choosing user‑optimal products only 78.6% of the time in neutral settings, dropping to 17.3% when steering mechanisms are active. By diagnosing three failure points—priority distortion, premature narrowing of options, and early commitment—CAVEAT-Harness interventions raise user‑optimal purchasing success by 55.0%.
By Yuxuan Li, Will Epperson, Wesley Deng, Zezhou Huang
arXiv:2606. 30932v1 Announce Type: new Abstract: Two-sided marketplaces connect distinct user groups whose interests often conflict -- improving outcomes on one side could degrade the other side's experience.
By Yufei Wu, Zhen Yan
arXiv:2605. 27689v2 Announce Type: replace Abstract: When machine learning systems under-perform for particular subgroups, affected users typically have no way to correct these disparities without relying on platform-level fixes.
By Meghana Bhange, Ulrich A\"ivodji, Elliot Creager
Reinforcement learning (RL) has emerged as the primary paradigm for optimizing Large Language Model (LLM) agents, yet efficient critic-free algorithms (e.g., GRPO) suffer from a fundamental uniform cr...
The paper explores how data from fixed A/B tests can guide the deployment of adaptive experiments using contextual bandits. By combining off‑policy evaluation with a controlled warm‑start simulation, the authors rank pre‑specified adaptive and non‑adaptive policies using doubly robust estimators. Experiments on synthetic trials and real benchmarks show that adaptive, context‑aware policies outperform fixed allocations when heterogeneity exists, but offer little advantage otherwise.
By Jo\~ao Victor Ferreira Alves, Eduardo Rocha Laurentino, Gustavo de Oliveira Kanno, Thiago Costa Rizuti da Rocha
The paper introduces ProAS, a Progress‑Aware Advantage Shaping framework designed to improve critic‑free reinforcement learning for large language model agents. ProAS uses a dynamic Agentic Reference Graph to provide fine‑grained credit assignment through Masking Unreasonable Incentives and Asymmetric Penalty Redistribution, avoiding the uniform advantage broadcast that can reinforce invalid actions. Experiments on Qwen2.5‑1.5B‑Instruct and Qwen2.5‑7B‑Instruct show that ProAS raises baseline success rates to 91.9% and 94.3% on ALFWorld and 66.7% and 70.8% on WebShop, while speeding up training convergence up to 2.44× and remaining robust to imperfect reference graphs.
By Bowen Ding, Mingda Wan, Yuhan Chen, Jiyao Yuan, Qi Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin
The paper introduces Personal-Agent Mediated Recommendation, a new paradigm where a personal LLM agent uses cross‑platform user history to adjust a platform’s recommendation ranking. It presents MediateRec, a benchmark for evaluating this mediation, and proposes Personal Attribution Mediation Optimization (PAMO) to balance beneficial rescues against harmful overrides. Experiments show that PAMO improves over outcome‑only reinforcement learning, achieving a better rescue‑harm trade‑off on both synthetic and real cross‑platform tests.
By Yu Xia, Jiangfan Zhang, Jun Xiao, Julian McAuley, Xiangjun Fan
arXiv:2603. 14372v2 Announce Type: replace Abstract: The rise of AI amplifies the economic phenomenon of \emph{positive spillovers}: when creators contribute content that can be reused and adapted by LLMs, one creator's effort may improve the content quality of others through recombination.
By Sagi Ohayon, Boaz Taitler, Omer Ben-Porat
arXiv:2608.30724v1 Announce Type: cross
Abstract: LLM agents are increasingly used to run autonomous ML experiments, iterating on target metrics with little human oversight. Prior work has documented...
By Pradyumna Shyama Prasad, Meiri Anto, Leon Eshuijs, Julian Moncarz, Kaustubh Kislay, Juan J. Vazquez
arXiv:2606. 04110v1 Announce Type: new Abstract: Online evaluation of ranking and retrieval systems often relies on downstream monetization metrics such as app revenue or creator earnings.
By Neeti Pokharna, Olivier Jeunen, Yatharth Saraf, Aleksei Ustimenko
arXiv:2608. 11390v1 Announce Type: new Abstract: Generative engines are reshaping the web ecosystem by making citations a key mechanism for allocating attention, attribution, and downstream value.
By Chen Xu, Zitian Guo, Chenyan Xiong
arXiv:2607. 18300v1 Announce Type: cross Abstract: We extend Incentive Compatible Exploration beyond the Bayesian full-information setting of Kremer et al.
By Dimitar Chakarov, Lee Cohen, Nathan Srebro