Foundation Models

• Agent Development Kit
  LLM Agent [https://google.github.io/adk-docs/agents/llm-agents/](https://google.github.io/adk-docs/agents/llm-agents/) Workflow Agent [https://google.github.io/adk-docs/agents/workflow-agents/](htt…
• Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
  Large language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human thought through repeated exposure to similar o…
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
  We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 are as follows: (1) De…
• Emergent Introspective Awareness in Large Language Models
  Injected “thoughts” In our first experiment, we explained to the model the possibility that “thoughts” may be artificially injected into its activations, and observed its responses on control trials …
• Equipping agents for the real world with Agent Skills
  As model capabilities improve, we can now build general-purpose agents that interact with full-fledged computing environments. Claude Code , for example, can accomplish complex tasks across domains us…
• Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
  Large language model (LLM) agents are increasingly built less by changing model weights than by reorganizing the runtime around them. Capabilities that earlier systems expected the model to recover in…
• NoveltyBench: Evaluating Language Models for Humanlike Diversity
  Language models have demonstrated remarkable capabilities on standard benchmarks, yet they struggle increasingly from mode collapse, the inability to generate diverse and novel outputs. Our work intro…
• SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
  Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their respective role in enhancing model generalization in rule-ba…