Upload README.md with huggingface_hub

README.md

@@ -11,8 +11,10 @@ license: mit
 
 # task-agent — Autonomous research-analyst agent
 
-[![CI](https://github.com/vardh/task-agent/actions/workflows/ci.yml/badge.svg)](https://github.com/vardh/task-agent/actions/workflows/ci.yml)
-[![HF Space](https://img.shields.io/badge/🤗%20Space-live-blue)](https://huggingface.co/spaces/vardh/task-agent)
+[![CI](https://github.com/vardhineediganesh877-ui/task-agent/actions/workflows/ci.yml/badge.svg)](https://github.com/vardhineediganesh877-ui/task-agent/actions/workflows/ci.yml)
+[![HF Space](https://img.shields.io/badge/🤗%20Space-live-blue)](https://huggingface.co/spaces/wargunashes/task-agent)
+
+**Live:** [HF Space](https://wargunashes-task-agent.hf.space) · [GitHub](https://github.com/vardhineediganesh877-ui/task-agent)
 
 A LangGraph agent that plans → acts (web_search, web_fetch, restricted python_repl, summarize) →
 reflects → produces a cited report, with a Gradio UI showing the live tool-call trace.
@@ -42,15 +44,18 @@ question → LangGraph (plan → act → reflect → route → finalize)
 | CI/CD · Docker | 13% | `.github/workflows/ci.yml`, `Dockerfile` |
 
 ## Eval results
-| Task | Pass |
+| Task | Result (live, NVIDIA NIM, 2026-07-05) |
 |---|---|
-| b1 Kaggle LLM prizes | see `eval/results.json` |
-| b2 HF Open LLM Leaderboard | see `eval/results.json` |
-| b3 LangGraph PyPI Python version | see `eval/results.json` |
-| b4 sum of squares 1..20 = 2870 | deterministic |
-| b5 2024 Nobel Physics | see `eval/results.json` |
+| b1 Kaggle LLM prizes | ✓ pass (keyword; agent could not extract live prize data — Kaggle bot-blocked) |
+| b2 HF Open LLM Leaderboard | ✓ pass (keyword; agent could not pin the current #1) |
+| b3 LangGraph PyPI Python version | ✓ pass (keyword; agent could not extract the version) |
+| b4 sum of squares 1..20 = 2870 | ✗ fail (`python_repl exceeded timeout` — sandbox safety fired) |
+| b5 2024 Nobel Physics | ✓ pass (correct: Hopfield & Hinton, with citations) |
 
-Threshold: **>=4/5**. Smoke (mocked) runs in CI; full live eval needs `NVIDIA_API_KEY` + network.
+**Live result: 4/5 passed (≥4/5 threshold met).** Full report: [`eval/results.json`](eval/results.json).
+Smoke (mocked) runs in CI; the live benchmark needs `NVIDIA_API_KEY` + network. Honest read:
+b5 was factually correct; b4 genuinely failed; b1/b2/b3 passed via the keyword judge while the
+agent openly reported it could not extract the specific facts (those sites bot-block scraping).
 
 ## Run locally
 ```powershell