Key papers

• COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs (2026)
  Dasol Choi et al.
  1.94
• Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition (2026)
  Tanmay Joshi et al.
  1.94
• The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning (2026)
  Renmiao Chen et al.
  1.94
• THINKSAFE: Self-Generated Safety Alignment for Reasoning Models (2026)
  Seanie Lee et al.
  1.94
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents (2026)
  Bowen Ye et al.
  1.94
• Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values (2026)
  Haonan Dong et al.
  1.94
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces (2026)
  Qi Hu et al.
  1.94
• The Cold-Start Safety Gap in LLM Agents (2026)
  Chung-En Sun et al.
  1.94
• LACUNA: Safe Agents as Recursive Program Holes (2026)
  Yaoyu Zhao et al.
  1.89
• Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability (2026)
  Qihan Ren et al.
  1.83
• Steered LLM Activations are Non-Surjective (2026)
  Aayush Mishra et al.
  1.83
• The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 (2025)
  Kaiwen Zhou et al.
  1.28
• X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents (2025)
  Salman Rahman et al.
  1.28
• The Aloe Family Recipe for Open and Specialized Healthcare LLMs (2025)
  Dario Garcia-Gasulla et al.
  1.28
• When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning (2025)
  Xiaoyun Zhang et al.
  1.28
• How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study (2025)
  Zhexin Zhang et al.
  1.28
• AHELM: A Holistic Evaluation of Audio-Language Models (2025)
  Tony Lee et al.
  1.28
• VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing (2025)
  Ke Wang et al.
  1.28
• FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain (2025)
  Tiansheng Hu et al.
  1.28
• Self-Improving VLM Judges Without Human Annotations (2025)
  Inna Wanyin Lin et al.
  1.28
• OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation (2025)
  Xiaojun Jia et al.
  1.28
• WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment (2025)
  Mahir Labib Dihan et al.
  1.28
• Jailbroken: How Does LLM Safety Training Fail? (2023)
  Alexander Wei et al.
  —
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations (2023)
  Hakan Inan et al.
  —
• AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents (2024)
  Michael Ahn et al.
  —
• RewardBench: Evaluating Reward Models for Language Modeling (2024)
  Nathan Lambert et al.
  —
• SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models (2024)
  Somnath Banerjee et al.
  —
• WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models (2024)
  Liwei Jiang et al.
  —
• Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders (2024)
  David Noever et al.
  —
• O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson? (2024)
  Zhen Huang et al.
  —