Read · 37 repos · 30 papers
Hugging Face
What agent builders are using on Hugging Face right now: benchmarks and trajectory datasets, tool-use and agent models, harness leaderboards, and the agent papers the community upvotes most. Our own reviews are in Papers.
Checked nightly, last on Nov 21, 2026. Ranked by Hugging Face's trending score; quantized re-uploads, uncensored variants, courses and templates are left out.
Datasets and benchmarks
- google/multimodal-knowledge-agent
85 likes · 7,529 downloads · since
- alphaXiv/AgentAlphaXiv
27 likes · 374 downloads · since
- AgentCyberRange/WebExploitBench-v1.2
30 likes · 7,727 downloads · since
- ukisai/Qwen3.8-27B-multi-turn-agent-sft
50 likes · 2,101 downloads · since
- google/asimov_agentic
44 likes · 1,471 downloads · since
- harness-hub/safeagents-judge-bench
30 likes · 2,357 downloads · since
- openbmb/UltraData-SFT-Agent-2609
324 likes · 13,745 downloads · since
- agents-last-exam/agents-last-exam
237 likes · 17,296 downloads · since
- SWE-bench/SWE-bench
45 likes · 16,149 downloads · since
- SWE-bench/SWE-bench_Lite
35 likes · 39,710 downloads · since
- Exgentic/agent-llm-traces
26 likes · 3,285 downloads · since
- glaiveai/glaive-function-calling-v2
541 likes · 17,496 downloads · since
- NousResearch/hermes-function-calling-v1
513 likes · 21,021 downloads · since
- lambda/hermes-agent-reasoning-traces
395 likes · 2,339 downloads · since
- ScaleAI/SWE-bench_Pro
209 likes · 40,978 downloads · since
- IntelligenceLab/Long-Horizon-Terminal-Bench
144 likes · 21,868 downloads · since
- gorilla-llm/Berkeley-Function-Calling-Leaderboard
143 likes · 74,528 downloads · since
- TeichAI/DeepSeek-v4-Pro-Agent
111 likes · 7,631 downloads · since
Spaces and leaderboards
- joelniklaus/harness-leaderboard
483 likes · since
- agent-memory-leaderboard/leaderboard
932 likes · since
- harness-hub/harness-lens
107 likes · since
- FineEnvs/multi-harness-rl
308 likes · since
- joelniklaus/harness-optimization
73 likes · since
- lvwerra/jupyter-agent-2
255 likes · since
- ibm-research/cuga-agent
106 likes · since
- google/ehr-navigator-agent-with-medgemma
71 likes · since
- Agents-MCP-Hackathon/healthcare-mcp-public
25 likes · since
- bstraehle/multi-agent-ai-autogen-coding
43 likes · since
Models
- kaushikvira/DeepSeek-V4.1-Flash-1017-GSQ-agentic-strata
53 likes · 19,801 downloads · text-generation · since
- InternScience/Agents-A1
671 likes · 2,314 downloads · text-generation · since
- S4MPL3BI4S/gemma4-coding-agent
37 likes · 6,488 downloads · since
- Qwen/Qwen-AgentWorld-35B-A3B
750 likes · 8,780 downloads · text-generation · since
- ByteDance-Seed/M3-Agent-Control
51 likes · 2,238 downloads · since
- lightonai/colgrep-agent-2B
39 likes · 1,088 downloads · text-generation · since
- alibaba-pai/AgenticQwen-8B
26 likes · 69 downloads · since
- InternScience/Agents-A1-FP8
25 likes · 287 downloads · text-generation · since
- Hobbylm/hobbylm-1B-computer-use
40 likes · 211 downloads · text-generation · since
Most upvoted agent papers, last two weeks
- TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks
165 upvotes on Hugging Face · Nov 17, 2026
- VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender
87 upvotes on Hugging Face · Nov 11, 2026
- Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents
69 upvotes on Hugging Face · Nov 10, 2026
- Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization
56 upvotes on Hugging Face · Nov 9, 2026
- MIRIX-2.0: Multi-Agent Memory System
55 upvotes on Hugging Face · Nov 9, 2026
- SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations
51 upvotes on Hugging Face · Nov 15, 2026 · reviewed here
- WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detection
49 upvotes on Hugging Face · Nov 16, 2026 · reviewed here
- SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection
45 upvotes on Hugging Face · Nov 4, 2026
- ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models
44 upvotes on Hugging Face · Nov 16, 2026
- PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers?
44 upvotes on Hugging Face · Nov 5, 2026
- MMFlash: Faster Speculative Decoding for Vision-Language Models
42 upvotes on Hugging Face · Nov 13, 2026
- PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models
42 upvotes on Hugging Face · Nov 12, 2026
- Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning
41 upvotes on Hugging Face · Nov 9, 2026
- Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents
38 upvotes on Hugging Face · Nov 12, 2026
- The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements
37 upvotes on Hugging Face · Nov 17, 2026 · reviewed here
- SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering
36 upvotes on Hugging Face · Nov 10, 2026
- Frontier3DBench: Benchmarking Coding Agents for 3D Creation across Objects, Scenes, and Interactive Open Worlds
29 upvotes on Hugging Face · Nov 6, 2026
- Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development
28 upvotes on Hugging Face · Nov 18, 2026
- InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure
27 upvotes on Hugging Face · Nov 8, 2026
- FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance
25 upvotes on Hugging Face · Nov 5, 2026
- Beneath the Surface: What We Overlook When We Talk About Agent Evolution
25 upvotes on Hugging Face · Nov 5, 2026
- AgentBaton: Efficient Model Collaboration in Agentic Tasks
24 upvotes on Hugging Face · Oct 25, 2026
- Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents
23 upvotes on Hugging Face · Nov 7, 2026
- Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages
23 upvotes on Hugging Face · Nov 6, 2026
- Video-Coder: Reinforcing Agentic Coding for Video Generation
22 upvotes on Hugging Face · Nov 6, 2026
- Unbundling Multimodal Vision Encoding
21 upvotes on Hugging Face · Nov 12, 2026
- G-CAST: Governed Continual Self-Training for E-Commerce Agents under Evolving Demands
20 upvotes on Hugging Face · Nov 13, 2026
- Accelerate Bench: Evaluating Agents for Application-Level Program Optimization
19 upvotes on Hugging Face · Nov 16, 2026 · reviewed here
- Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow
14 upvotes on Hugging Face · Nov 18, 2026
- From Repositories to Training Environments: Scaling Long-Horizon Coding Agents with Environment Evolution Loop
14 upvotes on Hugging Face · Nov 17, 2026 · reviewed here