Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
Paper • 2610.22273 • Published • 13
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives
Asap7772
authored a
paper 6 days ago
Asap7772
submitted a
paper to Daily Papers 6 days ago
NCJ
submitted a
paper to Daily Papers 9 days ago
NCJ
submitted a
paper to Daily Papers about 2 months ago
gist-sparse-attention
submitted a
paper to Daily Papers 4 months ago
Post
525
Shipped v0.1.2 of vtx — a minimalist coding agent for the terminal.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono — same principles, pure Python, no transpiled runtime.
What ships out of the box:
→ Textual TUI + headless CLI (vtx -p "fix the failing test")
→ 49 LLM provider gateways, all declared in a single provider.yaml
→ 5 core tools (read / edit / write / bash / find) plus web search and fetch
→ Session tree with compaction, handoff, and resume
→ AGENTS.md / CLAUDE.md auto-discovery
→ Skills system — drop SKILL.md files in .agents/skills/ and they become slash commands
→ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
→ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono — same principles, pure Python, no transpiled runtime.
What ships out of the box:
→ Textual TUI + headless CLI (vtx -p "fix the failing test")
→ 49 LLM provider gateways, all declared in a single provider.yaml
→ 5 core tools (read / edit / write / bash / find) plus web search and fetch
→ Session tree with compaction, handoff, and resume
→ AGENTS.md / CLAUDE.md auto-discovery
→ Skills system — drop SKILL.md files in .agents/skills/ and they become slash commands
→ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
→ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
awwkl
submitted a
paper to Daily Papers 6 months ago
Xkev
submitted a
paper to Daily Papers 9 months ago
adityatadimeti
authored a
paper 11 months ago
Asap7772
authored 3
papers about 1 year ago
Personalized Preference Fine-tuning of Diffusion Models
Paper • 2501.06655 • Published • 1
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
Paper • 2502.17387 • Published • 8
RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
Paper • 2510.02263 • Published • 9
Post
3,448
🚀 Ever dreamed of training your own Large Language Model from scratch? What if I told you it doesn't require a supercomputer or PhD in ML? 🤯
Introducing LLM Trainer - the educational framework that makes LLM training accessible to EVERYONE! Whether you're on a CPU-only laptop or scaling to distributed GPUs, we've got you covered. 💻➡️🖥️
Why LLM Trainer? Because existing tools are either too simplistic (hiding the magic) or too complex (requiring expert knowledge). We bridge the gap with:
🎓 Educational transparency - every component built from scratch with clear code
💻 CPU-first approach - start training immediately, no GPU needed
🔧 Full customization - modify anything you want
📈 Seamless scaling - from laptop to cluster without code changes
🤝 HuggingFace integration - works with existing models & tokenizers
Key highlights:
✅ Built-in tokenizers (BPE, WordPiece, HF wrappers)
✅ Complete Transformer implementation from scratch
✅ Optimized for CPU training
✅ Advanced features: mixed precision, gradient checkpointing, multiple generation strategies
✅ Comprehensive monitoring & metrics
Perfect for:
- Students learning transformers
- Researchers prototyping new ideas
- Developers building domain-specific models
Ready to train your first LLM? It's easier than you think!
🔗 Check it out: https://github.com/HelpingAI/llm-trainer
📚 Docs: Getting Started Guide
💬 Join the community: GitHub Discussions
#AI #MachineLearning #LLM #DeepLearning #OpenSource #Python #HuggingFace #NLP
Special thanks to HuggingFace and PyTorch teams for the amazing ecosystem! 🙏
Introducing LLM Trainer - the educational framework that makes LLM training accessible to EVERYONE! Whether you're on a CPU-only laptop or scaling to distributed GPUs, we've got you covered. 💻➡️🖥️
Why LLM Trainer? Because existing tools are either too simplistic (hiding the magic) or too complex (requiring expert knowledge). We bridge the gap with:
🎓 Educational transparency - every component built from scratch with clear code
💻 CPU-first approach - start training immediately, no GPU needed
🔧 Full customization - modify anything you want
📈 Seamless scaling - from laptop to cluster without code changes
🤝 HuggingFace integration - works with existing models & tokenizers
Key highlights:
✅ Built-in tokenizers (BPE, WordPiece, HF wrappers)
✅ Complete Transformer implementation from scratch
✅ Optimized for CPU training
✅ Advanced features: mixed precision, gradient checkpointing, multiple generation strategies
✅ Comprehensive monitoring & metrics
Perfect for:
- Students learning transformers
- Researchers prototyping new ideas
- Developers building domain-specific models
Ready to train your first LLM? It's easier than you think!
🔗 Check it out: https://github.com/HelpingAI/llm-trainer
📚 Docs: Getting Started Guide
💬 Join the community: GitHub Discussions
#AI #MachineLearning #LLM #DeepLearning #OpenSource #Python #HuggingFace #NLP
Special thanks to HuggingFace and PyTorch teams for the amazing ecosystem! 🙏
- 1 reply
Post
4,191
🚀 Dhanishtha-2.0-preview-0825 Is Here
The Intermediate Thinking Model just leveled up again.
With sharper reasoning, better tool use, and expanded capabilities, Dhanishtha-2.0-preview-0825 is now live and ready to impress.
🧠 What Makes Dhanishtha Special?
Unlike typical CoT models that only thinks one time, Dhanishtha thinks iteratively:
> Think → Answer → Rethink → Improve → Rethink again if needed.
🔗 Try it now: HelpingAI/Dhanishtha-2.0-preview-0825
🔞 Dhanishtha NSFW Preview
For those exploring more expressive and immersive roleplay scenarios, we’re also releasing:
HelpingAI/Dhanishtha-nsfw
A specialized version tuned for adult-themed interactions and character-driven roleplay.
🔗 Explore it here: HelpingAI/Dhanishtha-nsfw
💬 You can also try all of these live at chat.helpingai.co
The Intermediate Thinking Model just leveled up again.
With sharper reasoning, better tool use, and expanded capabilities, Dhanishtha-2.0-preview-0825 is now live and ready to impress.
🧠 What Makes Dhanishtha Special?
Unlike typical CoT models that only thinks one time, Dhanishtha thinks iteratively:
> Think → Answer → Rethink → Improve → Rethink again if needed.
🔗 Try it now: HelpingAI/Dhanishtha-2.0-preview-0825
🔞 Dhanishtha NSFW Preview
For those exploring more expressive and immersive roleplay scenarios, we’re also releasing:
HelpingAI/Dhanishtha-nsfw
A specialized version tuned for adult-themed interactions and character-driven roleplay.
🔗 Explore it here: HelpingAI/Dhanishtha-nsfw
💬 You can also try all of these live at chat.helpingai.co
- 4 replies
Post
3,178
🎉 Dhanishtha-2.0-preview-0725 is Now Live
The Intermediate Thinking Model just got even better.
With the new update, Dhanishtha is now sharper, smarter, and trained further on tool use
🧠 What Makes Dhanishtha Different?
Unlike standard COT models that give one-shot responses, Dhanishtha thinks in layers:
> Think → Answer → Rethink → Improve → Rethink again if needed.
HelpingAI/Dhanishtha-2.0-preview-0725
The Intermediate Thinking Model just got even better.
With the new update, Dhanishtha is now sharper, smarter, and trained further on tool use
🧠 What Makes Dhanishtha Different?
Unlike standard COT models that give one-shot responses, Dhanishtha thinks in layers:
> Think → Answer → Rethink → Improve → Rethink again if needed.
HelpingAI/Dhanishtha-2.0-preview-0725
Post
3,131
🎉 Dhanishtha 2.0 Preview is Now Open Source!
The world's first Intermediate Thinking Model is now available to everyone!
Dhanishtha 2.0 Preview brings revolutionary intermediate thinking capabilities to the open-source community. Unlike traditional reasoning models that think once, Dhanishtha can think, answer, rethink, answer again, and continue rethinking as needed using multiple
🚀 Key Features
- Intermediate thinking: Think → Answer → Rethink → Answer → Rethink if needed...
- Token efficient: Uses up to 79% fewer tokens than DeepSeek R1 on similar queries
- Transparent thinking: See the model's reasoning process in real-time
- Open source: Freely available for research and development
HelpingAI/Dhanishtha-2.0-preview
https://helpingai.co/chat
The world's first Intermediate Thinking Model is now available to everyone!
Dhanishtha 2.0 Preview brings revolutionary intermediate thinking capabilities to the open-source community. Unlike traditional reasoning models that think once, Dhanishtha can think, answer, rethink, answer again, and continue rethinking as needed using multiple
<think> blocks between responses.🚀 Key Features
- Intermediate thinking: Think → Answer → Rethink → Answer → Rethink if needed...
- Token efficient: Uses up to 79% fewer tokens than DeepSeek R1 on similar queries
- Transparent thinking: See the model's reasoning process in real-time
- Open source: Freely available for research and development
HelpingAI/Dhanishtha-2.0-preview
https://helpingai.co/chat
- 2 replies
Post
4,733
Introducing Dhanishtha 2.0: World's first Intermediate Thinking Model
Dhanishtha 2.0 is the world's first LLM designed to think between the responses. Unlike other Reasoning LLMs, which think just once.
Dhanishtha can think, rethink, self-evaluate, and refine in between responses using multiple <think> blocks.
This technique makes it Hinghlt Token efficient it Uses up to 79% fewer tokens than DeepSeek R1
---
You can try our model from: https://helpingai.co/chat
Also, we're gonna Open-Source Dhanistha on July 1st.
---
For Devs:
🔑 Get your API key at https://helpingai.co/dashboard
Dhanishtha 2.0 is the world's first LLM designed to think between the responses. Unlike other Reasoning LLMs, which think just once.
Dhanishtha can think, rethink, self-evaluate, and refine in between responses using multiple <think> blocks.
This technique makes it Hinghlt Token efficient it Uses up to 79% fewer tokens than DeepSeek R1
---
You can try our model from: https://helpingai.co/chat
Also, we're gonna Open-Source Dhanistha on July 1st.
---
For Devs:
🔑 Get your API key at https://helpingai.co/dashboard
from HelpingAI import HAI # pip install HelpingAI==1.1.1
from rich import print
hai = HAI(api_key="hl-***********************")
response = hai.chat.completions.create(
model="Dhanishtha-2.0-preview",
messages=[{"role": "user", "content": "What is the value of ∫0∞𝑥3/𝑥−1𝑑𝑥 ?"}],
stream=True,
hide_think=False # Hide or show models thinking
)
for chunk in response:
print(chunk.choices[0].delta.content, end="", flush=True)
- 2 replies
Kameshr
updated a
dataset over 1 year ago
Kameshr
published a
dataset over 1 year ago
Post
9,150
🚀AraClip is now fully integrated with Hugging Face 🤗
AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasks🔥
🔗 Try it out 🔗
🤖 model: Arabic-Clip/araclip
🧩 Gradio demo: Arabic-Clip/Araclip-Simplified
🌐 website: https://arabic-clip.github.io/Arabic-CLIP/
AraClip is a specialized CLIP model that was created by @pain and optimized for Arabic text-image retrieval tasks🔥
🔗 Try it out 🔗
🤖 model: Arabic-Clip/araclip
🧩 Gradio demo: Arabic-Clip/Araclip-Simplified
🌐 website: https://arabic-clip.github.io/Arabic-CLIP/
- 2 replies