{"total":25,"rows":[{"id":"2604.14858","title":"Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex","created":"2026-04-16","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2605.31140","title":"EvoDefense: Co-Evolving Black-Box Defense with Large Language Models","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2601.13655","title":"Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2601.01739","title":"K-EXAONE Technical Report","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2602.07954","title":"Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation","created":"2026-02-08","cited_by_count":2,"area":null},{"id":"2607.19913","title":"JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2607.25857","title":"Shieldstral","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2601.10804","title":"BYOL: Bring Your Own Language Into LLMs","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2603.26511","title":"AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.05630","title":"One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.12265","title":"How Useful Is Cross-Domain Generalization for Training LLM Monitors?","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.23974","title":"AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.26968","title":"RedVox: Safety and Fairness Gaps in Speech Models Across Languages","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.26820","title":"Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.04322","title":"DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.01210","title":"Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.13734","title":"PolicyMem: Geometric Policy Memory for LLM Governance","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.25715","title":"LingLan: An Advancing Traditional Chinese Medicine Diagnosis LLM with Multimodal Data","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.29266","title":"Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.35117","title":"Tool Mediation Alters Refusal Mechanisms in Large Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.02920","title":"HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.12313","title":"Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13626","title":"SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19811","title":"Calibration and Risk-Budgeted Decisions with System One Models","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}