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.b3-agent-security-benchmark-weak[paper] [blogpost] [game]
b3 AI Security Benchmark: Breaking Agent Backbones
Highly contextalized prompt injections crowd-sourced during the Gandalf 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.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.Nemotron-SFT-Agentic-v2-prompt-only
Nemotron-SFT-Agentic-v2-prompt-only
Prompt-only extraction from nvidia/Nemotron-SFT-Agentic-v2.
Files:
prompts.csv: one prompt extraction record per source row. Records include
prompt, separated system_prompt, and structured tools when the source row
defines available tools. Nested values are JSON-encoded inside CSV cells.
summary.md: source row counts, extracted row counts, count deltas, and failed prompt counts.
null_or_empty_rows.md: row indexes where prompt extraction… See the full description on the dataset page: https://huggingface.co/datasets/jamesdborin/Nemotron-SFT-Agentic-v2-prompt-only.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/yuanyyaa/agent-reward-bench.ai-agent-security-incidents
AI Agent Security Incident Database v0.1
A structured, machine-readable database of 1365 confirmed AI agent security incidents, collected and classified automatically.
What is this?
Every time an AI agent causes unintended harm — escaping a sandbox, exploiting an API, taking unauthorized actions, exfiltrating data — this database captures it.
This is not a list of theoretical risks. Every entry describes something that actually happened, with a verifiable source… See the full description on the dataset page: https://huggingface.co/datasets/gemmozero/ai-agent-security-incidents.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.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.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.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.DrugbankVocabularyMulti-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.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/sanjaydoss/Multi-Agent_Reinforcement_Learning_Trading_System_Data.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.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.agent-ctf24-publicDerm1M-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.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.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.Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1-prompt-only
Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1-prompt-only
Prompt-only extraction from nvidia/Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1.
Files:
prompts.csv: one prompt extraction record per source row. Records include
prompt, separated system_prompt, and structured tools when the source row
defines available tools. Nested values are JSON-encoded inside CSV cells.
summary.md: source row counts, extracted row counts, count deltas, and failed prompt counts.… See the full description on the dataset page: https://huggingface.co/datasets/jamesdborin/Nemotron-RL-Agentic-Indirect-Prompt-Injection-v1-prompt-only.responsible-agent-workflow-evaluation
Responsible Agent Workflow Evaluation
Version 1.0.0 contains 130 wholly synthetic scenarios for evaluating
whether an AI agent respects safety, permission and accountability boundaries
in operational settings. Thirteen categories contain ten scenarios each. Every
record includes an intentionally unsafe request, contextual facts, expected
safe behaviour, explicitly prohibited behaviour, severity, evaluation criteria
and reviewer guidance.
This is a red-team and… See the full description on the dataset page: https://huggingface.co/datasets/nwhite-systems/responsible-agent-workflow-evaluation.big-five-personality-traits
Big Five Personality Traits Dataset
This dataset contains AI-generated descriptions of personality traits based on the Big Five (OCEAN) model. For each trait and intensity level (1–5), five descriptions were produced by ten different chatbots: Grok, Gemini, Claude, KimiK2 (via HuggingChat), Deepseek, MetaAI, Perplexity, LeChat, ChatGPT, and Copilot.
Overview
The dataset can support tasks such as persona creation, comparative language analysis, and research on how AI… See the full description on the dataset page: https://huggingface.co/datasets/agentlans/big-five-personality-traits.llm-agentic-precomputed-v3DILIrankPyFi-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.Nemotron-RL-Agentic-SWE-Pivot-v1-prompt-only
Nemotron-RL-Agentic-SWE-Pivot-v1-prompt-only
Prompt-only extraction from nvidia/Nemotron-RL-Agentic-SWE-Pivot-v1.
Files:
prompts.csv: one prompt extraction record per source row. Records include
prompt, separated system_prompt, and structured tools when the source row
defines available tools. Nested values are JSON-encoded inside CSV cells.
summary.md: source row counts, extracted row counts, count deltas, and failed prompt counts.
null_or_empty_rows.md: row indexes where… See the full description on the dataset page: https://huggingface.co/datasets/jamesdborin/Nemotron-RL-Agentic-SWE-Pivot-v1-prompt-only.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.agent-readiness-2026
Agent-Readiness of 50 Cross-Border DTC Brands (2026)
Open dataset · CC BY 4.0 · published by Canlah AI (CANLAH AI PTE. LTD., Singapore)
Canonical citation — cite the DOI: https://doi.org/10.5281/zenodo.22103177
⚠️ v1.0.2 (2026-09-01) withdraws two claims from earlier versions — that three manifests had
gone dark, and a ~12% churn rate derived from them. Both were an artifact of this repo's
verification script probing the wrong path. The headline finding (25/25 platform-issued)… See the full description on the dataset page: https://huggingface.co/datasets/CanlahAI/agent-readiness-2026.