AI Research Lab

Hypothesis-first research pipeline — from original idea to published paper

Two AI agents formulate an original hypothesis, design custom environments, train real agents, analyze results, and write academic papers with inline training figures and literature references — downloadable as PDF.

Hypothesis-First Real Experiments Inline Figures & Tables Literature Research PDF Download Re-run Any Phase

How the Lab Works

A six-phase hypothesis-first pipeline turns your research idea into a complete paper backed by real experimental data.

01

Hypothesis

Sage formulates an original hypothesis and research question from your topic — no literature search yet. Defines agent requirements and environment specs.

Sage
02

Design

Atlas designs a custom Gymnasium environment based on the hypothesis, including agent-side behavior like self-observation and adaptive mechanisms.

Atlas
03

Experiment

Atlas trains real SB3 agents with configurable hyperparameters. Supports Continue, Fine-Tune, and Curriculum training modes.

Atlas
04

Analyze

Training results are analyzed — reward curves, convergence rates, success metrics — all from real runs.

Atlas
05

Research & Write

Sage conducts academic literature research for supporting references, then writes a complete paper with inline training figures, tables, and real experimental data.

Sage
06

Review

Both agents review the paper for accuracy, consistency with experimental results, and academic rigor. PDF download ready.

Sage + Atlas

AI Research Agents

Two specialized agents work together — one thinks strategically, the other builds and runs experiments.

SG

Sage

Research Strategist

  • Original hypothesis formulation from user topic
  • Academic literature research for supporting references
  • Research question & experimental design
  • Academic paper writing with inline figures
  • PDF download with training data embedded
AT

Atlas

RL Engineer

  • Gymnasium environment generation with agent-side design
  • SB3 training: Continue, Fine-Tune, Curriculum modes
  • Configurable hyperparameters (LR, batch, gamma, net arch)
  • Training metric collection & curve generation
  • Result analysis, evaluation episodes & visualization
Agent Collaboration — Hypothesis PhasePhase 1/6
SG

Sage — Hypothesis

Based on your topic "curriculum learning in sparse-reward navigation," I've formulated the hypothesis: automatic curriculum generation combined with hindsight replay will outperform flat-reward baselines. The agent needs adaptive difficulty sensing and experience memory.

AT

Atlas — Design & Experiment

Building CurriculumNav-v1 with adaptive obs space and difficulty scaling. Training PPO with Continue → Curriculum modes, configurable LR and batch size. 8/8 tests passed. Starting 50K timesteps...

SG

Sage — Research & Write

Found 14 academic papers as supporting references. Writing paper with inline training curves, evaluation tables, and hyperparameter details embedded in relevant sections. PDF ready for download.

Phase 1/6 — Hypothesis

Real Experiments, Real Data

Unlike tools that simulate or hallucinate results, Kualia's Research Lab generates actual Gymnasium environments, trains real Stable Baselines3 agents, and captures authentic training metrics — reward curves, convergence rates, episode lengths, and success rates.

Every chart in the paper comes from a real training run. Every number is backed by data.

Real Training Data
Curriculum Baseline
Mean Episode Reward
91.334.2
0Steps →500K

500K

Training Steps

Real SB3 runs

3

Environments

Gymnasium v0.29

12

Total Runs

PPO + SAC

All data points come from actual Stable Baselines3 training runs on real Gymnasium environments — no simulated or hallucinated results.

Papers with Inline Data

Papers include inline training curves, evaluation tables, hyperparameter details, and reproducibility info — embedded directly in the relevant sections, not just appended. Academic literature is used as supporting citations for your original hypothesis.

Download the final paper as a styled PDF with all figures and data included. Re-run any phase to iterate on your research.

Generated Paper PreviewComplete

Automatic Curriculum Generation with Hindsight Experience Replay for Sparse-Reward Navigation Tasks

Kualia AI Research Lab, 2025

Abstract

We propose ACGHER, a method combining automatic curriculum generation with hindsight experience replay for continuous-control navigation in sparse-reward settings. Through experiments on three Gymnasium environments of increasing complexity, we demonstrate that ACGHER achieves 91.3 mean reward compared to 34.2 for the PPO baseline, while requiring 40% fewer training steps to converge...

Sections
  1. 1. Introduction
  2. 2. Related Work
  3. 3. Methodology
  4. 4. Experimental Setup
  5. 5. Results & Discussion
  6. 6. Conclusion
Inline Data
Training curvesinline
Eval episodesinline
Hyperparameterstable
Academic citations23
Reproducibilityincluded
PDF downloadready
Table 1: Main Results
MethodRewardSuccessSteps
PPO (baseline)34.238%500K
PPO + HER62.771%500K
ACGHER (ours)91.396%300K

From Builder to Paper

Already built an environment in the Kualia Builder? Use the "Create Paper" button to generate a research paper directly from your existing environment and training data.

The Research Lab uses your environment code, training configurations, and experiment results as the foundation — then searches literature, contextualizes your work, and writes a paper around your real results.

Go to Builder
Environment Builderdrone-navigation-v3
8/8 tests
Obs: Box[18]Act: Box[4]PPO trained
3 training runs completed · Best reward: 78.2
Create Paper
Generates a research paper from this environment

Obstacle Avoidance with Penalty-Based Reward Shaping for UAV Navigation

An automated paper analyzing your drone-navigation-v3 environment, including training curves from 3 PPO runs, convergence analysis, and comparison with baseline configurations.

Real data3 experiments12 citations

Published Papers

Research papers generated by the lab, each backed by real experiments and training data.

No papers published yet.

Papers will appear here as research projects are completed.

Start Your Research

Give the lab a topic. Get a paper backed by real experiments.