Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications
Paper • 2603.08806 • Published • 7
AI & ML interests
None defined yet.
tzafrir
authored a
paper 3 months ago
tzafrir
submitted a
paper to Daily Papers 3 months ago
seun-ajayi
authored a
paper 7 months ago
Post
5340
OpenAI is now open again! Check out OpenAI’s brand new gpt‑oss‑20b model hosted on ZeroGPU 🤗
merterbak/gpt-oss-20b-demo
merterbak/gpt-oss-20b-demo
huggingface pro subscription
➕ 8
220
#4 opened over 1 year ago
by 
cyber98
Can't join the ai-starter-pack org
➕🔥 5
37
#5 opened about 1 year ago
by 
Dragoy
Can't join the ai-starter-pack org
➕🔥 5
37
#5 opened about 1 year ago
by Dragoy
huggingface pro subscription
➕ 8
220
#4 opened over 1 year ago
by cyber98
huggingface pro subscription
➕ 8
220
#4 opened over 1 year ago
by cyber98
huggingface pro subscription
➕ 8
220
#4 opened over 1 year ago
by cyber98
Can't join the ai-starter-pack org
➕🔥 5
37
#5 opened about 1 year ago
by Dragoy
reach-vb
updated a
Space about 1 year ago
Post
5633
Qwen 3 technical report released🚀
Report: https://github.com/QwenLM/Qwen3/blob/main/Qwen3_Technical_Report.pdf
Report: https://github.com/QwenLM/Qwen3/blob/main/Qwen3_Technical_Report.pdf
Post
2675
Seed-Coder released and it's designed for coding tasks, featuring base, instruct, and reasoning variants at an 8B parameter scale developed by ByteDance Seed team. Unlike traditional open source LLMs that rely on human crafted rules or annotated data for curating code pretraining datasets Seed-Coder introduces a model-centric data pipeline. The pipeline processes raw data from GitHub and web archives into four categories: file-level codes, repository-level codes, GitHub commits, and code-related web data.A quality filter LLM, evaluates code (for readability, modularity, clarity, and reusability) by removing the lowest 10% to create a 6 trillion token dataset supporting 89 programming languages.
Models: ByteDance-Seed/seed-coder-680de32c15ead6555c75b0e4
Github: https://github.com/ByteDance-Seed/Seed-Coder/tree/master
Paper: https://github.com/ByteDance-Seed/Seed-Coder/blob/master/Seed-Coder.pdf
Models: ByteDance-Seed/seed-coder-680de32c15ead6555c75b0e4
Github: https://github.com/ByteDance-Seed/Seed-Coder/tree/master
Paper: https://github.com/ByteDance-Seed/Seed-Coder/blob/master/Seed-Coder.pdf
Post
1728
Microsoft released their new fine-tuned phi-4 models with reasoning data yesterday. They outperform/rival much larger models . Check out them if you haven't yet. 🚀
Phi4 mini reasoning(SFT): microsoft/Phi-4-mini-reasoning
Phi-4 reasoning(SFT): microsoft/Phi-4-reasoning
Phi-4 reasoning plus (SFT + RL): microsoft/Phi-4-reasoning-plus
Demo: https://github.com/marketplace/models/azureml/Phi-4-reasoning/playground
Articles: https://arxiv.org/pdf/2504.21318
https://arxiv.org/pdf/2504.21233
Blog: https://azure.microsoft.com/en-us/blog/one-year-of-phi-small-language-models-making-big-leaps-in-ai/
Phi4 mini reasoning(SFT): microsoft/Phi-4-mini-reasoning
Phi-4 reasoning(SFT): microsoft/Phi-4-reasoning
Phi-4 reasoning plus (SFT + RL): microsoft/Phi-4-reasoning-plus
Demo: https://github.com/marketplace/models/azureml/Phi-4-reasoning/playground
Articles: https://arxiv.org/pdf/2504.21318
https://arxiv.org/pdf/2504.21233
Blog: https://azure.microsoft.com/en-us/blog/one-year-of-phi-small-language-models-making-big-leaps-in-ai/
- 1 reply
Post
5468
Qwen 3 models released🔥
It offers 2 MoE and 6 dense models with following parameter sizes: 0.6B, 1.7B, 4B, 8B, 14B, 30B(MoE), 32B, and 235B(MoE).
Models: Qwen/qwen3-67dd247413f0e2e4f653967f
Blog: https://qwenlm.github.io/blog/qwen3/
Demo: Qwen/Qwen3-Demo
GitHub: https://github.com/QwenLM/Qwen3
✅ Pre-trained 119 languages(36 trillion tokens) and dialects with strong translation and instruction following abilities. (Qwen2.5 was pre-trained on 18 trillion tokens.)
✅Qwen3 dense models match the performance of larger Qwen2.5 models. For example, Qwen3-1.7B/4B/8B/14B/32B perform like Qwen2.5-3B/7B/14B/32B/72B.
✅ Three stage done while pretraining:
• Stage 1: General language learning and knowledge building.
• Stage 2: Reasoning boost with STEM, coding, and logic skills.
• Stage 3: Long context training
✅ It supports MCP in the model
✅ Strong agent skills
✅ Supports seamless between thinking mode (for hard tasks like math and coding) and non-thinking mode (for fast chatting) inside chat template.
✅ Better human alignment for creative writing, roleplay, multi-turn conversations, and following detailed instructions.
It offers 2 MoE and 6 dense models with following parameter sizes: 0.6B, 1.7B, 4B, 8B, 14B, 30B(MoE), 32B, and 235B(MoE).
Models: Qwen/qwen3-67dd247413f0e2e4f653967f
Blog: https://qwenlm.github.io/blog/qwen3/
Demo: Qwen/Qwen3-Demo
GitHub: https://github.com/QwenLM/Qwen3
✅ Pre-trained 119 languages(36 trillion tokens) and dialects with strong translation and instruction following abilities. (Qwen2.5 was pre-trained on 18 trillion tokens.)
✅Qwen3 dense models match the performance of larger Qwen2.5 models. For example, Qwen3-1.7B/4B/8B/14B/32B perform like Qwen2.5-3B/7B/14B/32B/72B.
✅ Three stage done while pretraining:
• Stage 1: General language learning and knowledge building.
• Stage 2: Reasoning boost with STEM, coding, and logic skills.
• Stage 3: Long context training
✅ It supports MCP in the model
✅ Strong agent skills
✅ Supports seamless between thinking mode (for hard tasks like math and coding) and non-thinking mode (for fast chatting) inside chat template.
✅ Better human alignment for creative writing, roleplay, multi-turn conversations, and following detailed instructions.
Post
3640
FlowReasoner is a new system that builds a custom set of small AI agents for every user question. Unlike search based methods it uses reasoning driven optimization with external execution feedback.
✅ First, it distills reasoning data using DeepSeek R1-671B to build multi agent systems. 🤖
✅ Then, reasoning data used for DeepSeek-R1-Distill-Qwen-7B via supervised fine tuning for basic reasoning skills. 💡
✅ Finally, RL with GRPO (optimizes by comparing response groups from queries/tasks) to improve reasoning.
FlowReasoner: Reinforcing Query-Level Meta-Agents (2504.15257)
Code: https://github.com/sail-sg/flowreasoner
✅ First, it distills reasoning data using DeepSeek R1-671B to build multi agent systems. 🤖
✅ Then, reasoning data used for DeepSeek-R1-Distill-Qwen-7B via supervised fine tuning for basic reasoning skills. 💡
✅ Finally, RL with GRPO (optimizes by comparing response groups from queries/tasks) to improve reasoning.
FlowReasoner: Reinforcing Query-Level Meta-Agents (2504.15257)
Code: https://github.com/sail-sg/flowreasoner
Post
2371
Here’s a cool paper I found: “Massive Image Embedding Benchmark (MIEB).” It is a new tool to test how good image embedding models are. It has 130 different tasks grouped into 8 categories, like image search, classification, clustering similar images, answering questions based on images, and understanding documents. It even covers 38 different languages.
The authors tested 50 models and found that no single model was best at everything. Some models were great at recognizing text inside images but struggled to handle complicated tasks like matching images and text that appear together.
Paper: https://arxiv.org/pdf/2504.10471v1
Code: https://github.com/embeddings-benchmark/mteb
The authors tested 50 models and found that no single model was best at everything. Some models were great at recognizing text inside images but struggled to handle complicated tasks like matching images and text that appear together.
Paper: https://arxiv.org/pdf/2504.10471v1
Code: https://github.com/embeddings-benchmark/mteb
- 2 replies
Post
3076
OpenAI published 2 benchmark datasets on Hugging Face 🔥
openai/mrcr
openai/graphwalks
MRCR tests how well a model can find the right answer when many similar questions are spread out in a long context. Graphwalks checks if a model can follow steps in a big graph and find the correct nodes by thinking through the structure
openai/mrcr
openai/graphwalks
MRCR tests how well a model can find the right answer when many similar questions are spread out in a long context. Graphwalks checks if a model can follow steps in a big graph and find the correct nodes by thinking through the structure
Post
4035
OpenAI has released BrowseComp an open source benchmark designed to evaluate the web browsing capabilities of AI agents. This dataset comprising 1,266 questions challenges AI models to navigate the web and uncover complex and obscure information. Crafted by human trainers, the questions are intentionally difficult. (unsolvable by another person in under ten minutes and beyond the reach of existing models like ChatGPT with and without browsing and an early version of OpenAI's Deep Research tool.)
Blog Post: https://openai.com/index/browsecomp/
Paper: https://cdn.openai.com/pdf/5e10f4ab-d6f7-442e-9508-59515c65e35d/browsecomp.pdf
Code in simple eval repo: https://github.com/openai/simple-evals
Blog Post: https://openai.com/index/browsecomp/
Paper: https://cdn.openai.com/pdf/5e10f4ab-d6f7-442e-9508-59515c65e35d/browsecomp.pdf
Code in simple eval repo: https://github.com/openai/simple-evals