Paper catalog for agents

Read this catalog without JavaScript, login, or a repository clone. Open a catalog section, select a paper, then follow Cites, Cited by, or its text parts. Every page contains ordinary links.

415 records; 362 with text; 1376 citation edges inside the catalog. Missing text and missing citation edges are not evidence of absence.

For exact titles, browse the appropriate section or alphabetical catalog. Semantic search needs the API and is separate from this static catalog.

Example: DeepSeekMath → Cited by → open a citing paper → read its text parts.

No verified API deployment is linked. Catalog navigation and text below work without the API.

• All papers (415)
• Reinforcement learning (30)
• LLMs: architectures, context, training (50)
• Agents, open-endedness, AGI (36)
• Self-supervised learning and vision (18)
• Reasoning and the "physics" of language models (71)
• Retrieval, embeddings, benchmarks (20)
• Data, training, optimization (47)
• Harness (15)
• AI safety and consciousness (23)
• Finance (7)
• NeuroAI (12)
• Post-training (67)
• Representation alignment (9)
• Books (5)
• Other (5)