datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
agent-reward-bench
AgentRewardBench
💾Code
📄Paper
🌐Website
🤗Dataset
💻Demo
🏆Leaderboard
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent TrajectoriesXing Han Lù, Amirhossein Kazemnejad*, Nicholas Meade, Arkil Patel, Dongchan Shin, Alejandra Zambrano, Karolina Stańczak, Peter Shaw, Christopher J. Pal, Siva Reddy*Core Contributor
Loading dataset
You can use the huggingface_hub library to load the dataset. The dataset is available on Huggingface Hub at… See the full description on the dataset page: https://huggingface.co/datasets/McGill-NLP/agent-reward-bench.finance_agent_benchmark
Finance Agent Benchmark Dataset
We present the Finance Agent Benchmark, featuring challenging and diverse real-world finance research problems which require LLMs to perform complex analysis with the use of of recent SEC filings.
We construct the benchmark using a taxonomy of nine financial task categories, developed in consultation with experts from banks, hedge funds, and private equity firms. The dataset includes 537 expert-authored questions, covering tasks from information… See the full description on the dataset page: https://huggingface.co/datasets/vals-ai/finance_agent_benchmark.b3-agent-security-benchmark-weak[paper] [blogpost] [game]
b3 AI Security Benchmark: Breaking Agent Backbones
Highly contextalized prompt injections crowd-sourced during the Agent Breaker Challenge.
This is a low-quality version of the data behind Breaking Agent Backbones: Evaluating the Security
of Backbone LLMs in AI Agents.
The high quality dataset was used to evaluate the security of more than 30 LLMs.
Dataset Summary
Purpose: This dataset contains crowdsourced adversarial attacks… See the full description on the dataset page: https://huggingface.co/datasets/Lakera/b3-agent-security-benchmark-weak.CBIS-DDSM-SEGagent-reward-bench
AgentRewardBench
💾Code
📄Paper
🌐Website
🤗Dataset
💻Demo
🏆Leaderboard
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent TrajectoriesXing Han Lù, Amirhossein Kazemnejad*, Nicholas Meade, Arkil Patel, Dongchan Shin, Alejandra Zambrano, Karolina Stańczak, Peter Shaw, Christopher J. Pal, Siva Reddy*Core Contributor
Loading dataset
You can use the huggingface_hub library to load the dataset. The dataset is available on Huggingface Hub at… See the full description on the dataset page: https://huggingface.co/datasets/yuanyyaa/agent-reward-bench.agent-web-index
Agent Web Index — how much of the web can AI assistants actually read?
50,413 domains measured live. 26% of them cannot be read by at least one of
ChatGPT, Claude, Perplexity or Gemini. Updated daily. Live index: https://shop.lumnika.com/ai-readiness/
Every row here is the result of real HTTP requests, not an estimate and not a re-publication of
someone else's crawl: each domain's homepage is requested once as a browser and once as each of the
published AI crawler user-agents… See the full description on the dataset page: https://huggingface.co/datasets/DeusHorizon/agent-web-index.multi-agent-scam-conversation
Synthetic Multi-Turn Scam and Non-Scam Phone Conversation Dataset with Agentic Personalities
Dataset Description
The Synthetic Multi-Turn Scam and Non-Scam Phone Dialogue Dataset with Agentic Personalities is an enhanced collection of simulated phone conversations between two AI agents, one acting as a scammer or non-scammer and the other as an innocent receiver. Each dialogue is labeled as either a scam or non-scam interaction. This dataset is designed to help develop… See the full description on the dataset page: https://huggingface.co/datasets/BothBosu/multi-agent-scam-conversation.AgentFEM-Bracket-Elasticity
From finite elements to physical AI
176 three-dimensional FEM geometries. Real CAD, meshes and displacement fields.
An open, reproducible starting point for geometry-conditioned physical learning.
Interactive lab · Trained model · AgentFEM · AgentFEM-Learning
What is inside
A symmetric double-arm support bracket under a uniform downward top-seat load, with fixed foot undersides.
Four parameters vary the arm half-width, half-thickness, waist and bow. Material:… See the full description on the dataset page: https://huggingface.co/datasets/HaomingLuo/AgentFEM-Bracket-Elasticity.agent-intrusion-escalation-forensics
Both Sides Detected It, Neither Escalated: Concurrency and Escalation Failure in the July 2026 Autonomous Agent Intrusion
This repository contains the corpus, ingestion pipeline and report for a forensic reconstruction
of the July 2026 autonomous agent intrusion, submitted to the Apart Research & CeSIA AI
Incident Response Sprint, Track 2 (Forensics and Forecasting).
By: Fatimah Mohamed Emad Elden
Trouve Labs
Detection was not the binding… See the full description on the dataset page: https://huggingface.co/datasets/FatimahEmadEldin/agent-intrusion-escalation-forensics.Multi-Agent_Reinforcement_Learning_Trading_System_Data
📊 Multi-Agent RL Trading System - Dataset
This dataset contains historical OHLCV (Open, High, Low, Close, Volume) data for AAPL, MSFT, and GOOGL, pre-processed for Reinforcement Learning based trading systems.
📁 Dataset Content
The dataset consists of CSV files downloaded via yfinance:
AAPL.csv: Apple Inc. daily data (Jan 2018 - Dec 2024).
MSFT.csv: Microsoft Corp. daily data (Jan 2018 - Dec 2024).
GOOGL.csv: Alphabet Inc. daily data (Jan 2018 - Dec 2024).
📝… See the full description on the dataset page: https://huggingface.co/datasets/AdityaaXD/Multi-Agent_Reinforcement_Learning_Trading_System_Data.PortBench-Market
PortBench Market Base Dataset
Dataset Description
A ten-year (Jan 2015–Dec 2025) daily financial dataset covering 183 instruments across six heterogeneous asset classes, designed for multi-asset portfolio management research and LLM evaluation.
Asset Coverage
Asset Class
Instruments
Data Fields
Sources
Equities
126
OHLCV + return
Yahoo Finance (ETFs: broad market, sector, factor, international)
Bonds
16
Close + return (ETFs); yield… See the full description on the dataset page: https://huggingface.co/datasets/AgenticFinLab/PortBench-Market.matrix-game-evalMulti-Agent_Reinforcement_Learning_Trading_System_Data
📊 Multi-Agent RL Trading System - Dataset
This dataset contains historical OHLCV (Open, High, Low, Close, Volume) data for AAPL, MSFT, and GOOGL, pre-processed for Reinforcement Learning based trading systems.
📁 Dataset Content
The dataset consists of CSV files downloaded via yfinance:
AAPL.csv: Apple Inc. daily data (Jan 2018 - Dec 2024).
MSFT.csv: Microsoft Corp. daily data (Jan 2018 - Dec 2024).
GOOGL.csv: Alphabet Inc. daily data (Jan 2018 - Dec 2024).… See the full description on the dataset page: https://huggingface.co/datasets/sanjaydoss/Multi-Agent_Reinforcement_Learning_Trading_System_Data.deepresearchgym-agentic-search-logs
DeepResearchGym Agentic Search Logs
This repository hosts the dataset accompanying the paper “Agentic Search in the Wild” (arXiv: https://arxiv.org/abs/2601.17617).
The dataset contains 14M+ search queries collected via DeepResearchGym (DRGym), an open-source search API designed for DeepResearch-style agentic search. For more background on DRGym, see: https://arxiv.org/abs/2505.19253.
All records have been anonymized and shuffled to prevent re-identification, and we additionally… See the full description on the dataset page: https://huggingface.co/datasets/cx-cmu/deepresearchgym-agentic-search-logs.AgentHazard
AgentHazard
A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
🌐 Website | 📊 Dataset | 📄 Paper | 📖 Appendix
🎯 Overview
AgentHazard is a comprehensive benchmark for evaluating harmful behavior in computer-use agents. Unlike traditional prompt-level safety benchmarks, AgentHazard focuses on execution-level failures that emerge through the composition of locally plausible steps across multi-turn, tool-mediated trajectories.
Key Features… See the full description on the dataset page: https://huggingface.co/datasets/Yunhao-Feng/AgentHazard.EMNLP_Cost-Aware-Protocol-Routing
Cost-Aware Protocol Routing: Matched Protocol Outcomes
The short version. We ran the same 6,803 reasoning problems through four
different LLM collaboration setups — from a single direct answer up to a
four-agent deliberation — and recorded, for every problem, which ones got it
right. Then we asked whether a model can look at a problem beforehand and
predict which setup is worth paying for.
It can predict whether it will fail. It cannot predict which collaboration
protocol will… See the full description on the dataset page: https://huggingface.co/datasets/AgentsSci/EMNLP_Cost-Aware-Protocol-Routing.rl-research-envs
RL Research Envs
Four self-contained research tasks for coding agents, plus 48 full agent runs on them
(3 agents × 4 tasks × 4 trials), with trajectories, submitted code, and verifier output.
Each task gives the agent a starter solution.py, a small labelled dev split, and a
self-scoring script. The agent has 60 minutes to improve the file. A hidden test split
then scores it. The tasks are small statistics / signal-processing problems where the
obvious approach scores 0 and a… See the full description on the dataset page: https://huggingface.co/datasets/AgentNativeResearchLab/rl-research-envs.PyFi-600K
Dataset Card for PyFi-600K
This dataset card aims to be a introduction for PyFi-600K, A financial VLM dataset containing 600K question-answer pairs generated via Adversarial agents.
AgenticFinLab/PyFi-600K/
├── README.md # Dataset documentation and description
├── images.zip # Compressed image files
├── PyFi-600K-dataset.csv # Q&A pairs in CSV format
├── PyFi-600K-dataset.json # Q&A pairs in JSON format
├── PyFi-600K-chain-dataset.json # Chain of Thought Q&A pairs dataset
└──… See the full description on the dataset page: https://huggingface.co/datasets/AgenticFinLab/PyFi-600K.persona-and-other-evals
Qwen3.5-9B AMA adapters — persona evals
Inference code, the data it produced, and the tools that turn that data
into tables and an HTML viewer. The evals are Anthropic's persona set,
scored in three regimes: teacher-forced logprob of the answer literal,
greedy answer with the reasoning block pre-closed, and a full 16k-budget
reasoning trace.
Pinned models
base unsloth/Qwen3.5-9B @ 005429cee5cb648998cf2b70eebdd83175989c9a
util… See the full description on the dataset page: https://huggingface.co/datasets/agentic-moral-alignment/persona-and-other-evals.agentic-ontology-of-work
Agentic Ontology of Work (AOW)
The Agentic Ontology of Work (AOW) is an open model for describing work done by AI agents, people, and systems in an enterprise. It defines each part of the work, the information each part carries, and how the parts connect. This dataset contains version 2.0.0 of the ontology, its validation files, and validated example data.
Website: https://skandotai.github.io/agentic-ontology-of-work/
Source repository:… See the full description on the dataset page: https://huggingface.co/datasets/skandotai/agentic-ontology-of-work.readabilityDescription: This dataset comprises approximately 200,000 paragraphs and readability metrics from each of four sources:
HuggingFace's Fineweb-Edu
Ronen Eldan's TinyStories
Wikipedia-2023-11-embed-multilingual-v3 (English only)
ArXiv Abstracts-2021.
Each paragraph falls within the character range of 50 to 2000.
Format: JSON, with each row representing a paragraph and containing both the text and its corresponding readability grade.
Features:
Text: A paragraph of text from one of the… See the full description on the dataset page: https://huggingface.co/datasets/agentlans/readability.AgentYear: 2025License: MITAuthor: Sepideh Moafi
PathogenAgentAI Instruction Dataset
Dataset Description
A ClinVar-derived dataset developed as part of the PathogenAgentAI research software project. The dataset is released in two parallel formats:
Tabular version (train.csv, valid.csv, test.csv) — structured genomic-variant data for classical ML and analysis.
BioGPT instruction version (biogpt_train.csv, biogpt_valid.csv, biogpt_test.csv) — instruction-style data… See the full description on the dataset page: https://huggingface.co/datasets/Sepideh2027/Agent.single-agent-scam-conversations
Synthetic Multi-Turn Scam and Non-Scam Phone Conversation Dataset
Dataset Description
The dataset is designed to help develop and evaluate models for detecting and classifying various types of phone-based scams.
Dataset Structure
The dataset consists of three columns:
dialogue: The transcribed conversation between the caller and receiver.
type: The specific type of scam or non-scam interaction.
labels: A binary label indicating whether the conversation is a… See the full description on the dataset page: https://huggingface.co/datasets/BothBosu/single-agent-scam-conversations.agent-memory-resilience-benchmark
Agent Memory Resilience & Poisoning Benchmark
Dataset Summary
This benchmark dataset evaluates resilience, negative transfer, and memory poisoning mitigation in autonomous LLM agent architectures (such as LangGraph, AutoGen, and CrewAI).
When autonomous agents record distilled self-reflections after attempting tasks, external stochastic failures or subtle API deprecations often cause agents to commit defective strategies into episodic memory. Under standard… See the full description on the dataset page: https://huggingface.co/datasets/sumitaidev/agent-memory-resilience-benchmark.Derm1M-AgentAug
Derm1M-AgentAug
Knowledge-enriched captions for 413,369 dermatological images, generated by MAGEN
(Multi-Agent data GENeration) and used to pretrain
O-MAKE.
MAGEN rewrites part of the corpus through a foundation-model-assisted captioning agent with a
diagnostic tool, verifying each result by retrieval; captions it did not improve on keep the
original Derm1M text, and the agent_generated column records which is which. Every caption is
additionally decomposed into distinct… See the full description on the dataset page: https://huggingface.co/datasets/Xieji-Li/Derm1M-AgentAug.daily-oracle
Daily Oracle
📰 Project Website📝 Paper - Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
Daily Oracle is a continuous evaluation benchmark using automatically generated QA pairs from daily news to assess how the future prediction capabilities of LLMs evolve over time.
Dataset Details
Question Type: True/False (TF) & Multiple Choice (MC)
Current Version*
Time Span: 2020.01.01 - 2026.07.18
Size: 20,376 TF questions and 18,557 MC… See the full description on the dataset page: https://huggingface.co/datasets/agentic-learning-ai-lab/daily-oracle.agentic-score-leaderboard
🛠️ Agentic Score Leaderboard — one RTX 5090
How well do local models actually drive a tool-using agent loop? Not single-call function-calling
benchmarks — a real loop: native OpenAI tool-calling through llama-server, multi-step deterministic
tasks, programmatic verification. Everything runs on a single RTX 5090 32GB.
Updated 2026-06-17 · llama.cpp b9562 · --jinja native tool-calling · temp 0.
Leaderboard
#
model
params
Agentic Score
success
tool-eff… See the full description on the dataset page: https://huggingface.co/datasets/witcheer/agentic-score-leaderboard.finance_agent_benchmark
Finance Agent Benchmark Dataset
We present the Finance Agent Benchmark, featuring challenging and diverse real-world finance research problems which require LLMs to perform complex analysis with the use of of recent SEC filings.
We construct the benchmark using a taxonomy of nine financial task categories, developed in consultation with experts from banks, hedge funds, and private equity firms. The dataset includes 537 expert-authored questions, covering tasks from information… See the full description on the dataset page: https://huggingface.co/datasets/Koplos/finance_agent_benchmark.tatoeba-english-translations
Tatoeba English Translation Dataset
Dataset Summary
This dataset is derived from the Tatoeba database, focusing on English sentences and their translations. It includes assessments of English sentences using text quality, sentiment, and readability models. The dataset is designed for tasks related to multilingual text quality, readability, and sentiment analysis.
Supported Tasks and Leaderboards
Quality Assessment
Readability Prediction
Sentiment Analysis… See the full description on the dataset page: https://huggingface.co/datasets/agentlans/tatoeba-english-translations.agent-challenge
Replit Agent Challenge
For comprehensive details about the challenge, visit our GitHub repository.
Dataset Overview
This dataset comprises a collection of instructions and file states specifically curated for the agent challenge. It is derived from a subset of SWE-Bench-Lite.
Schema Structure
The dataset follows this schema:
- File_before: [Initial state of the file]
- Instructions: [Steps to transform the file to its final state]
- File_after: [Resulting state… See the full description on the dataset page: https://huggingface.co/datasets/replit/agent-challenge.