Tagged articles

LLaDA2.2

2 articles · Page 1 of 1

Jul 28, 2026 · Artificial Intelligence

LLaDA2.2: The First Large‑Scale Agentic Diffusion Model and Its Breakthroughs

LLaDA2.2 introduces Levenshtein‑based edit operations, 128K native context, and block routing to turn diffusion language models into reliable agents, achieving competitive scores on 17 benchmarks, up to 1.64× higher throughput than comparable autoregressive models, and demonstrating a new path for agentic AI.

Agentic AILLaDA2.2Levenshtein editing

0 likes · 16 min read

LLaDA2.2: The First Large‑Scale Agentic Diffusion Model and Its Breakthroughs

AntTech

Jul 27, 2026 · Artificial Intelligence

LLaDA2.2 Released: Levenshtein Editing Enables Diffusion Language Models to Correct On-the-Fly

LLaDA2.2 introduces a Levenshtein‑based edit mechanism and the L‑EBPO reinforcement framework, allowing diffusion language models to delete and insert tokens during agent interactions, achieving near‑autoregressive accuracy (53.83 vs 55.74) and 1.64× higher BF16 throughput, plus an 8.6 % gain on SWE‑bench.

LLaDA2.2Levenshtein editingMoE

0 likes · 11 min read

LLaDA2.2 Released: Levenshtein Editing Enables Diffusion Language Models to Correct On-the-Fly