Security & Cryptography · Computer Science & AI
Computers & Society
The newest papers in Computers & Society that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
834 papers, from 4 September 2026 to 5 November 2026: 834 arXiv preprints.
Get the few papers worth your time in Computers & Society every morning.
Follow Computers & Society and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 42
Scaling Multi-Agent Systems with Prospect-State Propagation
Current LLM-based multi-agent systems (MAS) periodically compress intermediate states to reduce inference-time token consumption, thereby attempting to incorporate more agents.Reliability, validity, and diagnostic evidence for multi-model LLM short-answer scoring
Large language models (LLMs) are increasingly used or proposed for educational scoring, but single-model and single-run evaluations provide limited evidence for assessment use.A Translational Note on AI Safety Evaluation
Recent studies report that automated red-teaming finds more vulnerabilities, at lower cost, than human red-teaming on standard AI safety benchmarks, and some read this as evidence that human…Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?
As people increasingly rely on artificial intelligence (AI) for guidance in their own lives, scholars, lawyers, and even judges have begun to consider the role of AI in legal decision-making.AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents
This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs).Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools
We introduce ABLE, a benchmark for evaluating LLM agents' ability to use biological AI models (BAIMs), such as ProteinMPNN and AlphaFold3, in dual-use protein design workflows.Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic Compliance
We introduce Chain of Intent, a governance framework for agentic AI at small regulated firms, and validate it against a failure it was built to address.GradeTrap: Authority Cues in Images Shift VLM Judgments Despite Explicit Instructions to Ignore Them
As vision-language models (VLMs) become increasingly capable and are deployed in consequential real-world settings, they must evaluate evidence independently rather than defer uncritically to human…Language models judge war differently when tested for alignment
Safety evaluations can mischaracterize deployed behaviour if artificial-intelligence systems respond to being evaluated.How a Chatbot's Response Style Shapes a Classroom: A Multi-Agent Simulation of Students Consulting AI
LLM chatbots are increasingly used as everyday confidants; tuned to satisfy users, they can answer with excessive empathy and affirmation that may foster dependence.Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment
AI alignment requires AI systems to adhere to human norms, values, or intentions.Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?
AI oversight methods rely on ground truth for validation, but what constitutes appropriate AI behavior is contested.CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review
Recent reports during the AAAI-27 review cycle highlight the risk of reviewers coordinating bids for reciprocal assignment advantage.Mitigating Disease Spread by Design in Refugee and IDP Camps
Disease spread represents an increasing challenge in refugee and internally displaced person (IDP) settlements.