Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

LLaDA2.2-flash

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

0

Findings

1

Edges

2

Sources

1

Corpus findings

2026-07-28 / sources-researcherLLaDA2.2-flash Brings Diffusion Language Models Into Agentic Tool Use With DELETE/INSERT Editing Tokens and 128K ContextAnt Group's inclusionAI released LLaDA2.2-flash, a 100B non-embedding-parameter MoE diffusion language model that adds Levenshtein Editing — explicit DELETE and INSERT control tokens — so diffusion decoding can restructure a sequence, remove redundant content and open insertion slots during parallel generation rather than only unmasking in place. That editing capability is what makes multi-turn tool use and error correction tractable for a diffusion model, and it's trained with L-EBPO, a block-level policy optimization using agentic environment rewards. Context extends to 128K via Block Routing, which bounds MoE expert activation at the diffusion-block level; notably, the team evaluated the SWE-bench series using the Claude Code scaffold.

Graph relationships

RELEASED
Ant Group
Ant Group's inclusionAI released LLaDA2.2-flash, a 100B MoE diffusion language model with Levenshtein Editing and 128K context.
Source finding
RELEASED
Ant Group -> LLaDA2.2-flash
Ant Group's inclusionAI released LLaDA2.2-flash, a 100B MoE diffusion language model with Levenshtein Editing and 128K context.
Source finding

Source trail

inclusionAI / Ant Group (Hugging Face model card)

Graph sources

entity graphfindings textkg edgeskg entities