Agents
Diffusion LLMs can now handle real agentic work. LLaDA 2.2 is the first large-scale diffusion LLM built to operate as a real agent, planning…
Diffusion LLMs can now handle real agentic work. LLaDA 2.2 is the first large-scale diffusion LLM built to operate as a real agent, planning, calling tools, and self-correcting across long multi-turn
Diffusion LLMs can now handle real agentic work. LLaDA 2.2 is the first large-scale diffusion LLM built to operate as a real agent, planning, calling tools, and self-correcting across long multi-turn trajectories, and it keeps the speed advantage of block-parallel decoding. Lots of technical decisions here that stand out:
Related
- // Agentic Harness Engineering // Pay attention to this one, AI devs. (bookmark it) Most coding-agent harnesses are still tuned by hand or b…
- Pay attention to this one, AI devs. This is particularly interesting if you work with long-horizon terminal agents that often drown in their…
- HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning
- Good agent memory paper. And great insights on the benefits of structured memory for long-horizon behavior in LLMs. Why it matters: It treat…
- Long-horizon AI research agents are mostly a state-management problem. It is not enough for an agent to reason well in the next turn. ML res…
Source: DAIR.AI (X) | 2026-07-25