Spaces:
Configuration error
Configuration error
ychanakya12 commited on
Commit ยท
5f50076
1
Parent(s): 0f28872
Detailing Tri-Agent Ecosystem and final documentation fixes
Browse files
README.md
CHANGED
|
@@ -30,6 +30,26 @@ The agent leverages **GPT-OSS 20B** to make quarterly decisions across six cruci
|
|
| 30 |
|
| 31 |
---
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
## ๐ง Problem Statement
|
| 34 |
The **BusinessSimEnv** is a multi-turn, delayed-reward environment where every action has cascading consequences. A CEO must survive up to **8 quarters** (2 years) while maintaining:
|
| 35 |
* Positive cash flow in a recession.
|
|
@@ -44,76 +64,43 @@ The **AdversarialAgent** in the environment injects realistic "shocks" (budget a
|
|
| 44 |
Our agent implements a **Reasoning-Driven Control Loop** with the following advanced heuristics:
|
| 45 |
|
| 46 |
### ๐ 1. Proactive ROI Analysis
|
| 47 |
-
The agent
|
| 48 |
-
* Expected Profit * (1 - Total Risk).
|
| 49 |
-
* Quarterly Salary Burn (Salary per developer * count).
|
| 50 |
-
* Opportunity Cost of the team's resource pool.
|
| 51 |
|
| 52 |
### ๐ 2. Salary Optimization Hack
|
| 53 |
-
|
| 54 |
|
| 55 |
### ๐ก๏ธ 3. Bankruptcy Protection
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
### ๐ 4. Premium Stack Multiplier
|
| 59 |
-
By defaulting to a **Premium Tech Stack**, the agent reduces project risk and increases profit margins by 20%, which is the key to hitting the $150,000 budget target required for a perfect score in the Survival task.
|
| 60 |
|
| 61 |
---
|
| 62 |
|
| 63 |
-
##
|
| 64 |
-
|
| 65 |
-
1. **
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
cd business-sim-agent
|
| 69 |
-
```
|
| 70 |
-
|
| 71 |
-
2. **Configure Environment Variables**:
|
| 72 |
-
```bash
|
| 73 |
-
$env:HF_TOKEN="your_huggingface_token"
|
| 74 |
-
```
|
| 75 |
-
|
| 76 |
-
3. **Run Inference**:
|
| 77 |
-
```bash
|
| 78 |
-
python inference.py
|
| 79 |
-
```
|
| 80 |
-
|
| 81 |
-
4. **Validate Submission**:
|
| 82 |
-
```bash
|
| 83 |
-
python validate.py
|
| 84 |
-
```
|
| 85 |
-
|
| 86 |
-
---
|
| 87 |
-
|
| 88 |
-
## ๐จ Visualization
|
| 89 |
-
The agent provides a clean terminal output with `[START]`, `[STEP]`, and `[END]` markers, as required by the OpenEnv validator, making it fully compatible with automated leaderboard evaluation.
|
| 90 |
-
|
| 91 |
-
> *"Building a resilient business is not about never failing; it's about failing small and winning big."* โ **AI CEO Agent**
|
| 92 |
|
| 93 |
---
|
| 94 |
|
| 95 |
## ๐ ๏ธ Tech Stack & Dependencies
|
| 96 |
-
|
| 97 |
-
* **
|
| 98 |
-
* **
|
| 99 |
-
* **
|
| 100 |
-
* **Communication**: **Httpx** for asynchronous networking between the agent and the simulation.
|
| 101 |
|
| 102 |
---
|
| 103 |
|
| 104 |
-
##
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
3. **Cross-Scenario Generalization**: Ensuring the prompt heuristics work across Easy, Medium, and Hard tasks without manual parameter tuning.
|
| 109 |
|
| 110 |
---
|
| 111 |
|
| 112 |
-
##
|
| 113 |
-
|
| 114 |
-
*
|
| 115 |
-
*
|
| 116 |
-
* **Reinforcement Learning (PPO)**: Transitioning from heuristic prompts to a fine-tuned model specifically trained on BusinessSim trajectories.
|
| 117 |
|
| 118 |
---
|
| 119 |
|
|
|
|
| 30 |
|
| 31 |
---
|
| 32 |
|
| 33 |
+
## ๐ The Simulation Ecosystem: A Tri-Agent Interaction
|
| 34 |
+
Our simulation is not a static set of rules, but a dynamic, multi-agent world where the **AI CEO** must compete and survive against two other environmental agents:
|
| 35 |
+
|
| 36 |
+
### ๐ค 1. The AI CEO (The Decision Engine)
|
| 37 |
+
* **Role**: The primary protagonist of the simulation.
|
| 38 |
+
* **Actions**: Project acceptance, hiring/firing (Salary Optimization), tech stack selection, and skill training.
|
| 39 |
+
* **Objective**: Maximize long-term corporate health (Budget, Reputation, and Low Burnout) through high-reasoning ROI analysis.
|
| 40 |
+
|
| 41 |
+
### ๐ 2. The Market Agent (The Economic Engine)
|
| 42 |
+
* **Role**: Simulates the macro-economic environment and consumer demand.
|
| 43 |
+
* **Behavior**: Driven by a Markov Chain, this agent triggers **Boom, Stable, and Recession** cycles.
|
| 44 |
+
* **Impact**: It alters the Domain Demand multipliers (e.g., higher demand for AI during Booms) and profit variances, forcing the CEO to adapt their strategy quarterly.
|
| 45 |
+
|
| 46 |
+
### ๐ก๏ธ 3. The Adversarial Agent (The Friction Engine)
|
| 47 |
+
* **Role**: Simulates the "Chaos" of real-world business operations.
|
| 48 |
+
* **Behavior**: Injects randomized "Shocks" based on the simulation's difficulty level.
|
| 49 |
+
* **Impact**: Triggers events like **Budget Audits** (draining cash), **Key Employee Departures** (lowering skill), and **Client Disputes** (tanking reputation).
|
| 50 |
+
|
| 51 |
+
---
|
| 52 |
+
|
| 53 |
## ๐ง Problem Statement
|
| 54 |
The **BusinessSimEnv** is a multi-turn, delayed-reward environment where every action has cascading consequences. A CEO must survive up to **8 quarters** (2 years) while maintaining:
|
| 55 |
* Positive cash flow in a recession.
|
|
|
|
| 64 |
Our agent implements a **Reasoning-Driven Control Loop** with the following advanced heuristics:
|
| 65 |
|
| 66 |
### ๐ 1. Proactive ROI Analysis
|
| 67 |
+
The agent performs real-time **ROI** analysis factoring in Expected Profit, Total Risk, and Quarterly Salary Burn.
|
|
|
|
|
|
|
|
|
|
| 68 |
|
| 69 |
### ๐ 2. Salary Optimization Hack
|
| 70 |
+
The agent dynamically **fires developers** to instantly save ~$24,000 per quarter in overhead.
|
| 71 |
|
| 72 |
### ๐ก๏ธ 3. Bankruptcy Protection
|
| 73 |
+
Follows a strict **Budget-to-Penalty Ratio**. Skip the quarter rather than taking a "suicidal" gamble.
|
|
|
|
|
|
|
|
|
|
| 74 |
|
| 75 |
---
|
| 76 |
|
| 77 |
+
## ๐ Evaluation Methodology
|
| 78 |
+
Our agent is validated against three distinct "Gates":
|
| 79 |
+
1. **Unit Tests**: Verifying deterministic logic for budget calculations (`test_grade.py`).
|
| 80 |
+
2. **Adversarial Stress Test**: Running the Hard task (`adversarial_resilience`).
|
| 81 |
+
3. **Generalization**: Heuristics that work across all task difficulties.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
|
| 83 |
---
|
| 84 |
|
| 85 |
## ๐ ๏ธ Tech Stack & Dependencies
|
| 86 |
+
* **Core Logic**: Python 3.12+ with Pydantic schemas.
|
| 87 |
+
* **Inference**: **GPT-OSS 20B** on Hugging Face Router.
|
| 88 |
+
* **Environment API**: **FastAPI** simulation server.
|
| 89 |
+
* **Communication**: Asynchronous **Httpx**.
|
|
|
|
| 90 |
|
| 91 |
---
|
| 92 |
|
| 93 |
+
## ๐ฎ Future Roadmap (v2.0)
|
| 94 |
+
* **Multi-Agent Negotiation**: Direct negotiation with the Adversarial Agent.
|
| 95 |
+
* **Dynamic Tech Stacks**: Modular technology selection.
|
| 96 |
+
* **Reinforcement Learning (PPO)**: Transitioning from heuristic prompts to fine-tuned models.
|
|
|
|
| 97 |
|
| 98 |
---
|
| 99 |
|
| 100 |
+
## โ๏ธ Installation & Usage
|
| 101 |
+
1. **Configure Token**: `$env:HF_TOKEN="your_token"`
|
| 102 |
+
2. **Run Inference**: `python inference.py`
|
| 103 |
+
3. **Validate**: `python validate.py`
|
|
|
|
| 104 |
|
| 105 |
---
|
| 106 |
|