arXiv:2603.29759v1 Announce Type: cross Abstract: Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment. However, existing benchmarks suffer from three fundamental limitations: (1) heavy reliance on synthetic datasets constructed via simulation software, creating a significant domain gap with real-world environments; (2) oversimplified safety tasks with artificial constraints on hazard and scene types, thereby limiting model generalization; and (3) absence of rigorous evaluation protocols to thoroughly assess model capabilities in complex home safety scenarios. To address these challenges, we introduce TSHA (\textbf{T}rustworthy \textbf{S}afety \textbf{H}azards \textbf{A}ssessment), a comprehensive benchmark comprising 81,809 carefully curated training samples drawn from four complementary sources: existing indoor datasets, internet images, AIGC images, and newly captured images. This benchmark set also includes a highly challenging test set with 1707 samples, comprising not only a carefully selected subset from the training distribution but also newly added videos and panoramic images containing multiple safety hazards, used to evaluate the model's robustness in complex safety scenarios. Extensive experiments on 23 popular VLMs demonstrate that current VLMs lack robust capabilities for safety hazard assessment. Importantly, models trained on the TSHA training set not only achieve a significant performance improvement of up to +18.3 points on the TSHA test set but also exhibit enhanced generalizability across other benchmarks, underscoring the substantial contribution and importance of the TSHA benchmark.

arXiv:2603.29888v1 Announce Type: cross Abstract: In collaboration with Alibaba, this study leverages a large-scale field experiment to assess the impact of a generative AI assistant on worker performance in e-commerce after-sales service. Human agents providing digital chat support were randomly assigned with access to a gen AI assistant that offered two core functions: diagnosis of customer issues and solution proposals, presented as text messages. Agents retained discretion to adopt, modify, or disregard AI-generated messages. To evaluate gen AI's impact, we estimate both the intention-to-treat (ITT) effect of gen AI access and the local average treatment effect (LATE) of gen AI usage. Results show that gen AI significantly improved service speed, measured by issue identification time and chat duration. Gen AI also improved subjective service quality reflected in customer ratings and dissatisfaction rates, but it had no significant effect on objective service quality indicated by customer retrial rates. The performance improvements stemmed not only from automation but also from changes in the dynamics of agent-customer interactions: agent communication became more informative and efficient, while customers experienced reduced communication burdens. Low performers achieved the greatest improvements in both service speed and quality, narrowing the performance gap. In contrast, top-performing agents showed little improvement in service speed but experienced declines in both subjective and objective service quality. Evidence suggests that this decline results from increased multitasking tendency, proxied by longer shift-away times across concurrent chats, which slowed customer responses and raised abandonment and retrial rates. These findings suggest that gen AI reshapes work, demanding tailored deployment strategies.

arXiv:2603.20340v2 Announce Type: replace-cross Abstract: Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottleneck is not only skill generation quality, but the fact that web skills remain implicit and therefore cannot be checked or locally repaired. To address this, we present ContractSkill, a framework that converts a draft skill into an executable artifact with explicit procedural structure, enabling deterministic verifica tion, fault localization, and minimal local repair. This turns skill refinement from full rewriting into localized editing of a single skill artifact. Experiments on VisualWebArena show that Contract Skill is effective in realistic web environments, while MiniWoB provides a controlled test of the mechanism behind the gain. Under matched transfer layers, repaired artifacts also remain reusable after removing the source model from the loop, providing evi dence of portability within the same benchmark family rather than full-benchmark generalization. These results suggest that the central challenge is not merely generating skills, but mak ing them explicit, executable, and repairable. Code is available at https://github.com/underfitting-lu/contractskill.git.