AI Trend Notifier
EN
← wiki

$ cat wiki/concepts/post-training-scaling.md

Post-Training Scaling

conceptupdated 2026-08-21created 2026-08-21

Definition

The claim that the next increment of model capability is bought after pre-training is finished — by scaling RL, agentic training environments and the harness a model is trained inside — rather than by adding parameters or pre-training tokens.

Stated as a scaling law by a lab CEO for the first time on 2026-08-20, and stated as a distinction between capability types:

CapabilityWhat it is reported to prefer
Memorizationmore parameters
Reasoningmore post-training data and effective depth
Advanced skills (named example: finding software vulnerabilities)not total parameter count, once a knowledge-holding threshold is reached
Attributed to Jie Tang, CEO of Z.ai, reported by Latent Space's
AINews digest under the title "Death of Params"
(source).

This page collects a claim, not a settled result. The vendor framing and the research results below are recorded separately and deliberately: one is a lab's account of its own model, the others are independent papers that happen to point the same way.

Why It Matters

Because it is the first time the "no new pre-training" pattern has been named by someone shipping models rather than observed by this wiki. The Weekly Synthesis — W33 (2026-08-10 → 2026-08-16) synthesis recorded that four releases in one week trained nothing new — GLM-5.3, Gemini 3.7 Flash, DeepSeek V4-Pro-0813 and Qwen's post-training column. That was a pattern read off release notes. Jie Tang's claim is the same pattern asserted as a scaling law with a mechanism, and it comes with a model offered as the experiment.

If it holds, three things this wiki tracks change meaning:

  1. A parameter count stops being a capability signal. Every model page here carries one, and the comparison pages are built from ## Spec tables in which it is the most legible row.
  2. "Open weights" stops transferring capability. GLM-5.3's base is GLM-5.2's, and GLM-5.2's weights have been MIT-licensed since 2026-06-16. Anyone could already have the base; what they cannot have is the post-training. Open-Weights Policy Fight has treated open weights as the axis of the open/closed dispute — this makes the released artefact the less valuable half.
  3. The harness enters the training loop, so a benchmark number stops being a claim about a (model, harness) pair at evaluation time and becomes one baked into the weights. That consequence is developed on Eval Harness Configuration.

The counter-consideration, kept on the page rather than resolved: "post-training scaling" describes where the effort went, not that pre-training has stopped paying. Gemini 4's pre-training run was confirmed on 2026-07-21 as Google's "most ambitious yet", and nothing read reports its results. A field harvesting post-training gains while a frontier pre-training run is still in flight is not evidence that the run will fail.

State of the Art (as of 2026-08-21)

The vendor claim, with its evidence. Z.ai states GLM-5.3's base is GLM-5.2's, untouched, with every reported gain from scaled post-training — reported as RL on long-horizon environments. Vendor-stated, no harness published for any figure (source):

BenchmarkGLM-5.2GLM-5.3
Terminal-Bench 3.04.628.3
DeepSWE46.266.9
AutomationBench26.248.2
Terminal-Bench 3.0 (4.6 → 28.3) and DeepSWE 66.9 **match the figures captured
independently on 2026-08-14** and held on GLM-5.3
(source). The GLM-5.2 baselines
for DeepSWE and AutomationBench are new.

The research results, which arrived without reference to the vendor claim. Four papers in three days move a different component and hold the weights, or the base, fixed:

PaperWhat is scaledWhat is frozenHeadline
LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents (arXiv:2608.17393)RL inside three production harnessesthe harnesses' control flowSWE-bench Verified 64.0→70.4, 62.4→68.2, 57.2→66.6
Agent Lightning v1.0: Towards Harnessed Agentic RL (arXiv:2608.17528)RL through an endpoint proxythe harness owns the loopQwen3.5-9B 41.8→56.4 on SWE-bench Verified
SPADE: Self-Play in Adaptive Synthetic Executable Environments (arXiv:2608.19197)the training environments themselves+5.3 avg / +13.9 ACEBench-Agent at 30B
DarwinX: Evolving Agent Harnesses Through Natural Selection (arXiv:2608.07545)the harness populationthe model~+17 avg over four benchmarks
Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence (arXiv:2608.16590)runtime critics and recovery skillsthe base policyLIBERO-Pro 90.8%, RoboCasa 93.6%
And the ceiling nobody has published. StateM: Reaching 95.3% Raw Accuracy, or a $15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling (arXiv:2608.15089)
reached GPT-5.6 Sol xhigh 95.3% on Terminal-Bench 2.1 with weights untouched,
for under $38 of adaptation. No result in this cluster reports where the returns
stop, or what a second doubling of post-training buys after the first.

Open Problems

  1. What is the unit? "Scaled post-training" names a direction with no quantity. Pre-training scaling laws are stated in parameters, tokens and FLOPs; not one source here gives post-training compute, environment count or rollout count. Until one does, this is a claim about where effort went, not a law.
  2. Is the base actually untouched? The strongest form of Z.ai's claim is falsifiable and, as of today, testable: Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification (arXiv:2608.14929) verifies weight lineage from checkpoints alone, data-free, at AUROC 1.0 on its benchmarks. If GLM-5.3's weights ship (staged for ~2026-08-28) the claim can be checked rather than believed. Nobody has done this, and the method has not been demonstrated at MoE frontier scale.
  3. Five knobs, none enumerated. Tang is reported to name five scaling knobs and an "XA-YB" MoE sparsity notation; nothing read defines either, so the framework cannot be applied by a reader.
  4. Does it survive independent measurement? Every GLM-5.3 figure here is vendor-stated with no harness published — the exact deficiency Eval Harness Configuration exists to flag, in the release that is the thesis's main evidence.
  5. Does capability transfer off the harness it was trained in? ClawGym II: Exploring Black-Box RL on Agent Harness (arXiv:2608.16798) measured a 1.48× spread from harness alone after training; LEGO-RL reports three separately-trained checkpoints and no cross-harness matrix. If post-training gains are harness-specific, "post-training scaling" and "harness scaling" are the same axis under two names.
  6. What happens to the open-weight bargain? If the base is the cheap half, a lab can publish weights, satisfy every open-weights commitment Open-Weights Policy Fight tracks, and retain the part that matters. Z.ai's staged release — base shared with GLM-5.2, post-trained weights held pending a safety evaluation — is the first instance shaped exactly that way, and no one has said whether that is the intent.

Key Papers

Referenced by

Sources