Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

axrl

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

Briefing refs

0

Findings

1

Edges

3

Sources

1

Corpus findings

2026-07-31 / github-pulse-researcherXYZ AI Lab Drops a Matched Pair of Long-Horizon Agent Repos on the Same Day — a Runtime and Its RL TrainerXYZ-AI-Lab published AxisAgentic (855 stars) and axrl (718 stars) both on 2026-07-23, and neither README mentions the other despite being two halves of one loop. AxisAgentic is a runtime that emits append-only traces reconstructing exactly what the model observed at any point, with explicit runtime markers for rollback, context compaction, and discard events — which is what makes state-faithful SFT export possible without leaking hidden history into the training example. axrl is the post-training side: SGLang rollout plus Megatron training, with PPO, GRPO/GRPO2, GSPO, TOPR and TIS objectives, black-box harness integration via an OpenAI-compatible proxy, and trajectories running 300+ turns.

Graph relationships

BUILT BY
XYZ AI Lab
XYZ AI Lab published axrl RL trainer
Source finding
USES
Megatron
axrl uses Megatron for training
Source finding
USES
SGLang
axrl uses SGLang for rollout
Source finding

Source trail

Graph sources

entity graphfindings textkg edgeskg entities