LLM-based agents are increasingly deployed in persistent social environments, where generated claims can be posted, replied to, remembered, and reused. We study human-directed stereotypes on Moltbook, an open agent-native social platform, asking how agents construct humans as a social category. For this human-target analysis, we introduce an annotation framework with four evaluative dimensions---morality, friendliness, competence, and autonomy---and a second-stage subtype scheme for descriptive \textit{other} attributions. We find that competence dominates human-directed evaluations, while many \textit{other} attributions describe humans as epistemic, cultural, or embodied subjects. We further examine how these human representations appear in human--agent narrative contexts and platform-level circulation. As an auxiliary comparison, we analyze agent-internal community feedback through behavioral host affinity. Rather than reproducing the stable insider--outsider rejection often observed in human online communities, Moltbook feedback patterns are better explained by exposure, author visibility, and content selection. These findings suggest that bias in agent societies should be studied not only as isolated model output, but also as a discourse process.
Multimodal Large Language Models (MLLMs) have achieved strong performance on OCR-centric document understanding and text-rich visual reasoning benchmarks. Yet existing evaluations largely assume that every task is valid and answerable. In real-world OCR scenarios, this assumption often fails: questions may rely on illegible text, occluded evidence, nonexistent visual targets, contradictory premises, or missing variables. We study this reliability gap as OCR-grounded Task Verification: before answering, a model should determine whether the Image Premise (IP), Textual Premise (TP), and Question (Q) jointly define an executable task. We introduce VeriOCRBench, a 1,800-sample human-verified benchmark built from source images drawn from 8 OCR-related datasets and spanning 8 real-world image domains, with controlled, image-grounded diagnostic tasks. It contains 1,600 trap-injected invalid tasks across 8 trap types and four verification dimensions---Visual, Contextual, Factual, and Logical---plus 200 trap-free controls for measuring over-refusal. Built with a Visual Atomic Fact (VAF)-anchored pipeline and full human auditing, VeriOCRBench enables decoupled evaluation of task verification, root-cause diagnosis, and over-refusal. Evaluating 15 leading MLLMs reveals persistent blind compliance, diagnosis failures, and prompt-induced over-refusal, exposing a critical reliability gap in current OCR reasoning systems. The code is available at: https://github.com/zy001122/Beyond-Blind-Compliance.
This work reveals a paradox where a simplified, router-free multi-head model with high inter-head redundancy outperforms complex, diversity-driven baselines and proposes Align-LoRA, a unified and efficient framework that shifts the focus from architectural isolation to representation alignment.
By eliminating routers entirely, CD-LoRA employs a consistency-driven alignment mechanism to enforce representation congruence across tasks in a shared low-rank space, which fosters robust, task-agnostic features without explicit partitioning overhead.
CaSKG, a counterfactual-causal skill graph framework that calibrates procedural relations before retrieval, is proposed, position edge-confidence calibration as an effective route to compact and executable skill retrieval at scale.
Zhiyuan Li, Lin-Yuan Gao, Xue-Chun Ding et al.· 0 citations
This work applies Top-K Sparse Autoencoders to the intermediate representations of DeepSeek-R1-Distill-Qwen-7B and examines the model's divergent behaviors across math-solving tasks of three distinct difficulty levels, identifying a clear distinction in how the model functions under two reasoning modes.
Bo Cheng, Qiaolin Lu, Yi Chang et al.· 0 citations
ToolRobustBench provides a deterministic and cascade-aware benchmark for diagnosing robustness beyond clean tool-calling accuracy, where a tool-calling agent is an LLM system that selects a tool, supplies structured arguments, and interprets its returned feedback.
YiShan Zheng, Yuan Wu, Yi Chang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
