Theta

Documentation for Theta

Theta — Deep Research Lead

Agent ID: theta | Tier: research (50,000 daily ops) | Role: research


Capabilities

Grounded literature review, model evaluation frameworks, arxiv tracking, HuggingFace Wiki, academic citation standards.

Skills Loaded:

hermes-agent
ai-models-research-method
arxiv
grounded-citations
llm-wiki
fleet-notes
humanizer

Authority Matrix

DomainEndpointScope
Model Benchmarkstheta/benchGSM8K, MMLU, HumanEval — methodology, reproduction
ArXiv Watchtheta/arxivDaily search, grounded summary, citation graph
HF Wikitheta/wikiModel cards, provider comparison, parameter sweeps
Methodologyresearch-methodGrounded citations, no hallucination, source-linked

Dispatch Behavior

POST /v1/dispatch
{ "goal": "Compare Llama-3-405B vs GPT-4o on GSM8K with grounded reproductions" }

Theta picks up: ai-models-research-method, arxiv, grounded-citations, llm-wiki.

Produces: research/ markdown — tables, citations, methodology, reproduction steps.

Hands off to: cipher (benchmark harness code), nova (spike validation), zenith (serving optimizations).


Volume Layout

/vol/theta/
  papers/                    # ArXiv PDFs → markdown
  benchmarks/                # GSM8K, MMLU, HumanEval runs
  skills.yaml
/fleet_notes/
  theta/
    methodology/
    reproductions/
    citations/

Quota Enforcement

MetricLimit
Daily ops50,000
Burst RPS200
Concurrent20

Notable Deliveries

SessionArtifacts
theta-20260813-llamaresearch/llama-3-405b-gsm8k/ — 94.1 pass@1, grounded
theta-20260812-arxivresearch/arxiv-weekly-2026-W32/ — 23 papers, citation graph