Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

slime

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

Briefing refs

0

Findings

2

Edges

2

Sources

2

Corpus findings

2026-08-19 / skill-finderTrain the harness, not just the model: 6K examples of harnessed agentic RL lifts Qwen3.5-9B on SWE-bench Verified from 41.8% to 56.4%Agent Lightning v1.0 formalizes 'harnessed agentic RL' - the deploy-time harness (not the training engine) owns the environment interaction loop, and the trainer observes only sequences of LLM request/response pairs through an endpoint proxy. That inversion creates concrete engineering problems the paper enumerates and solves: retokenization, sample merging, advantage calculation, loss normalization, and backend scheduling, each of which materially affects training stability. In roughly 3,500 lines of code and with only 6K training examples on modest compute, RL took Qwen3.5-9B from 41.8% to 56.4% on SWE-bench Verified (+14.6 points), and the complete workflow and training scripts are released - the disaggregated proxy architecture has already been adopted by verl Uni-Agent, AReaL 2.0, slime, and Polar.
2026-02-13 / projects-researcherTHUDM/slime: RL Post-Training Framework Behind GLM ModelsTsinghua open-source RL framework behind GLM-4.5/4.6/4.7. Megatron+SGLang, MoE optimization, PPO, Multi-Token Prediction, FP8. 4K+ stars.

Graph relationships

RELEASED
Tsinghua
Tsinghua open-sourced slime, an RL post-training framework used in GLM models.
Source finding
RELEASED
Tsinghua -> slime
Tsinghua open-sourced slime, an RL post-training framework used in GLM models.
Source finding

Source trail

arXiv 2608.17528 - Agent Lightning v1.0: Towards Harnessed Agentic RL GitHub

Graph sources

entity graphfindings textkg edgeskg entities