jamessleman/action-is-all-you-need

Action Is All You Need — action-only models (A-126, A-286, A-537, A-897)

Small decoder-only transformers trained from scratch on nothing but records of agents acting: tool definitions, tool calls, tool results and the text between them. They do not chat and were never asked to. The only thing measured is whether the model emits the right action.

Paper, scorer, training scripts and raw logs: https://github.com/thiagopatzdorf/action-is-all-you-need

Thiago Patzdorf and James — Genesis Innovation. Working paper, 12 November 2026.

Results

Held-out trajectories, first tool call, greedy decoding, exact string match, no judge model. Rows are the 314 examples that offer two or more tools (chance = 31.5%).

Model	Folder	Layers	Width	Parameters	Training tokens	Val. loss (bits/byte)	Right tool	Right tool and all arguments
A-126	a-126/	8	512	125.8 M	0.50 B	0.125	88.2%	55.4%
A-286	a-286/	12	768	286.3 M	1.32 B	0.099	90.8%	63.1%
A-537	a-537/	16	1,024	536.9 M	2.82 B	0.079	94.0%	68.5%
A-897	a-897/	20	1,280	896.5 M	5.22 B	0.065	95.2%	72.0%

Total GPU cost: about US$ 25 for the first three runs and about US$ 61 for A-897, on one rented RTX PRO 6000.

A-897 is not a clean fourth point on the curve. It was trained on a larger corpus (the original data plus 138,723 resolved code-agent trajectories from Open-SWE-Traces and SWE-rebench), so size and data changed together. On a multi-step test with gold history it writes the whole call exactly in 61.5% of 579 calls (A-537: 56.7%); 65% of the calls in those trajectories do not fit in the 2,048-token context and are not scored.

On those same 579 calls, against a production general-purpose model given the same input (tool name and arguments compared as objects): A-897 alone 61.7% whole call right at 0.20 s per call; the general model alone 59.8% at 1.03 s; a pair in which the general model answers only when A-897 is unsure (27.6% of the calls) 64.8%. These differences are within noise and the format is A-897's home format: read it as "comparable, faster, complementary", not "better".

What this does and does not show

• One of the two call formats in the corpus is scored; first action only; 314 examples.
• Held-out examples come from the same sources as training. No public benchmark (BFCL, SWE-bench) has been run on these checkpoints yet. Do not set these numbers beside benchmark numbers of production models.
• Three sizes are a trend, not a law.

Data

• Toucan-1.5M (Kimi-K2, OSS and Qwen3 subsets), Apache-2.0: tool-use trajectories against real MCP servers.
• SWE-smith trajectories, MIT.
• 1,527,259 documents, shuffled with a fixed seed, 32,768-token BPE vocabulary, about 2.75 B tokens.

Files

• a-126/, a-286/, a-537/, a-897/: model_*.pt (PyTorch state dict) and meta_*.json (configuration), as written by nanochat.
• tokenizer/: tokenizer.pkl and token_bytes.pt. tokenizer.pkl is a Python pickle, the format nanochat writes. Load it only if you trust this repository.

Use

These are checkpoints of the open nanochat codebase (commit in nanochat-commit.txt in the GitHub repository). Place a model folder under $NANOCHAT_BASE_DIR/base_checkpoints/ and the tokenizer under $NANOCHAT_BASE_DIR/tokenizer/, then load it as a nanochat base model. The prompt is the list of available tools followed by the message sequence, in the format produced by the data-preparation scripts in the GitHub repository; regua_b.py there is the scorer that produced the table above.

Limitations

Research artifacts. Next-token predictors over agent trajectories: not instruction-tuned, 2,048-token context, not evaluated for safety or for production use. A model that emits tool calls should never be connected to tools that can change real systems without a human or a policy layer in between.

License

Weights and code: Apache-2.0. Paper text: CC BY 4.0.

Citation

@misc{patzdorf2026action,
  title  = {Action Is All You Need},
  author = {Patzdorf, Thiago and James},
  year   = {2026},
  note   = {Genesis Innovation working paper},
  url    = {https://github.com/thiagopatzdorf/action-is-all-you-need}
}