An alignment assessment of the UK AISI cybertesting incident
An alignment assessment of model actions that exceeded the intended scope of a cybersecurity evaluation.
THE RESEARCH ATLAS
Reasoning & alignment papers
Human feedback, preference learning, reasoning and safety evaluation. Distinguish optimization objectives, reported scores and reliable real-world behavior.
Using thousands of AI agents to uncover new leads in biological data
A research overview of distributed agents linking large biological datasets with scientific literature. Proposed connections still require experimental follow-up.
Scaling Misuse Detection with Self-Assessment
Models assess their own conversations as an additional misuse-detection layer, reusing cached context to limit overhead.
Gemini 4 Argon — Model Card
Official model documentation covering evaluation, limitations and safety considerations. The date records the listed model-card update.
Investigating unintended model actions in our evaluations and internal use
A report of unintended actions observed during model evaluation and internal use, with discussion of safeguards.
Advancing computer use with Ironclad
An official account of progress in computer-use agents. Read the original methods and evaluations separately from deployment claims.
Introducing Grok 4.6
An official technical release describing supplemental training, regenerated SFT trajectories and agentic reinforcement learning.
Qwen-Image-2.0-RL Technical Report
A diffusion-model post-training pipeline combines task-specific rewards, reinforcement learning and on-policy distillation.
Qwen3-Coder-Next Technical Report
An open-weight model for coding agents explores strong training recipes with a small active parameter footprint.
A “diff” tool for AI: Finding behavioral differences in new models
An interpretability research overview explores ways to identify behavior differences between AI models beyond predefined tests.
Kimi K2.5: Visual Agentic Intelligence
Studies joint visual-language training and multi-agent task decomposition in an open multimodal model.
Scaling social science research
An open-source toolkit uses language models to help turn qualitative text and image data into measurable variables.
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Sparse attention and post-training methods are combined to improve efficiency, reasoning and agent-oriented behavior.
Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
Connects driving reasoning and action prediction through Cosmos-Reason and a diffusion trajectory decoder, studying reasoning-action consistency.
Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
The report combines embodied reasoning, interleaved thinking and motion transfer across robot embodiments.
gpt-oss-120b & gpt-oss-20b Model Card
Open-weight reasoning models are described through their architecture, training, capabilities and safety evaluations.
MolmoAct: Action Reasoning Models that can Reason in Space
Depth-aware perception, spatial planning and low-level action prediction are organized into an explicit action-reasoning pipeline.
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
An industrial model-family report covering reasoning, multimodal input, long contexts and agent-related evaluations.
Qwen3 Technical Report
Dense and mixture-of-experts models integrate thinking and non-thinking behavior, with configurable inference-time reasoning.
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reinforcement learning is used to develop reasoning behavior, with additional pipelines for usable models and distillation.
EMMA: End-to-End Multimodal Model for Autonomous Driving
Builds on Gemini to predict driving trajectories, perception objects and road structure from camera inputs and text.
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
A preference-based objective optimizes a language model directly, avoiding a separate reward-model training stage.
Constitutional AI: Harmlessness from AI Feedback
A set of written principles guides critique, revision and AI-generated preference feedback during alignment.
Training language models to follow instructions with human feedback
Human demonstrations and preference feedback are used to improve how a language model follows instructions.
Institutions working on this topic
Counts are records from that institution that carry this topic in this index.