README.md

metadata

license: other
license_name: actionman-research-preview
license_link: LICENSE
library_name: pytorch
base_model: answerdotai/ModernBERT-large
tags:
  - action-model
  - function-calling
  - tool-calling
  - tool-use
  - non-autoregressive
  - masked-diffusion
  - modernbert
datasets:
  - Salesforce/xlam-function-calling-60k
  - Team-ACE/ToolACE
  - NousResearch/hermes-function-calling-v1

ActionMan-0.1

Decision models choose. Action models act.

ActionMan-0.1 is an action model: a 0.4B encoder that selects the tool in one forward pass and writes every argument with masked diffusion. It finishes in 2-3 forward passes, with no autoregressive decoding and no JSON generated.

One tool call, median, batch 1	latency
ActionMan-0.1 (RTX 4090)	17 ms
Qwen3-0.6B fine-tuned on the same data (vLLM, tuned, same GPU)	122 ms
GPT-6 Luna (API, network included)	1,455 ms

In the time GPT-6 Luna returns one call, ActionMan returns 85.

Inside

1. Encode. ModernBERT-large (28 layers, 395M weights) encodes the tool signatures, the instruction and up to four [CALL] markers once. The context is cached.
2. Select tool. Each [CALL] scores every tool, or none. A length head sizes the slots for every argument.
3. [MASK] slots. One block of masked slots is appended, covering every argument.
4. Denoise. All slots are predicted in parallel:
   • values that appear in the instruction are copied as spans;
   • enums and booleans are picked from their options;
   • lists get a count head and item slots.
5. Re-mask < 0.85, denoise. Low-confidence slots are re-masked and predicted again. The passes run as CUDA graphs.

A language model runs its full stack once per output token. The same call takes about 80 forward passes.

Speed

Latency is flat in the size of the answer:

	1 call	3+ calls
ActionMan-0.1	16.8 ms	21.0 ms
Qwen3-0.6B, vLLM	111 ms	331 ms

On a server CPU (8 threads), ActionMan fp32 takes 0.45 s and llama.cpp Q8_0 takes 1.66 s.

The Arena

Three real-time games played only through tool calls, where thinking time is charged to the model.

Wins out of 12	ActionMan-0.1	Qwen3-0.6B, same data	GPT-6 Luna
2D Minecraft	10	9	10
Rally	11	9	3
Cycling	11	3	3

Accuracy

BFCL v4, official harness	size	Non-Live	Live	Irrelevance
ActionMan-0.1	0.4B	66.0	45.1	81.2
Hammer2.1-0.5b	0.49B	65.9	54.7	80.7
granite-4.0-350m	0.35B	67.7	46.7	61.1
Qwen3-0.6B (FC)	0.75B	72.9	58.8	80.9
Qwen3-0.6B fine-tuned on the same data	0.75B	75.7	54.1	79.1
Qwen3-1.7B (FC)	2.0B	82.7	74.7	76.8
GPT-6 Luna (API, reasoning low)	-	78.2	68.8	75.6

• The run: every model ran with bfcl-eval==2026.3.23 on one box, single-turn categories only.
• Full report: per-category scores, confidence intervals and error classes are in benchmark.md.

Usage

pip install "git+https://github.com/shing1Sks/ActionMan"        # torch, transformers>=5, safetensors, huggingface_hub

from actionman.api import ActionMan

am = ActionMan.from_pretrained("shing-dev/ActionMan-0.1")    # compiles on GPU (one-off warm-up)
tools = [{"type": "function", "function": {
    "name": "get_weather", "description": "Current weather for a city",
    "parameters": {"type": "object", "properties": {
        "city": {"type": "string"}, "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}},
        "required": ["city"]}}}]
am.predict("What's the weather in Paris in celsius?", tools)
# [{"name": "get_weather", "arguments": {"city": "Paris", "unit": "celsius"}, "confidence": 0.9812}]
am.predict("Tell me a joke", tools)
# []

• Without pip: the inference code is also in this repo under code/actionman/. Add code/ to sys.path.
• No call: [] means no tool fits. require=True forces a call, like tool_choice="required".
• confidence is the minimum over the tool and every argument. Abstaining below a threshold works well: skipping the 10% least confident calls takes accuracy on our 2,340-prompt eval from 78.6 to 85.1.
• Specs:
  • single turn, English;
  • up to 4 calls per request;
  • lists of up to 7 items;
  • an input of about 896 tokens.

Training

• Data: 5 epochs over 80,459 rows:
  • xLAM-60k, 58,000;
  • ToolACE, 10,359;
  • Hermes v1, 1,100;
  • no-call examples, 11,000.
• Hardware: one RTX 4090, about 2 hours.

Licence

• The weights are for research use only. The training data includes Salesforce's xLAM-60k, whose card says "This release is for research purposes only."
• ToolACE and Hermes are Apache-2.0.
• The inference code is MIT.

Links

• Code, benchmarks, the Arena: github.com/shing1Sks/ActionMan
• The launch film: actionman-launch-film.mp4

Research by Shreyash Kumar Singh with an AI coding agent (Claude).