AI Bank Statement Analyzer (Made by the LangChain Community) Transform bank statements into queryable financial insights using AI. This system combines YOLO and LangChain's RAG to enable natural language analysis of your personal finances. Check it out here
LLMS
-
Qwen3-Max Thinking Available on Qwen Chat with 82k Token Budget
By
–
Qwen3-Max Thinking is now available on Qwen Chat with 82k tokens worth of thinking budget.
-
MaxKB: Open-Source Enterprise AI Agents with LangChain RAG
By
–
MaxKB AI Agents (Made by the LangChain Community) MaxKB is an open-source platform that builds enterprise AI agents using LangChain-powered RAG and workflows. It features multi-modal support and seamless integration with both private and public LLMs. Check it out here
-
Kimi Linear: Hybrid Attention Architecture Reduces KV Cache 75%
By
–
9. Kimi Linear Kimi Linear introduces a hybrid linear attention architecture combining Kimi Delta Attention (KDA) with periodic full attention layers at a 3:1 ratio, achieving superior performance over full attention while reducing KV cache by 75% and delivering 6× faster
-
Agent Data Protocol Standardizes LLM Agent Training Datasets
By
–
8. Agent Data Protocol Agent Data Protocol introduces a standardized format to unify fragmented agent training datasets across different tools and interfaces, enabling more efficient fine-tuning of LLM agents.
-
Stress-Testing LLM Constitutional Specifications and Behavioral Guidelines
By
–
7. Stress-Testing Model Specs This research examines how well large language models adhere to their stated behavioral guidelines by stress-testing AI constitutional specifications through value-tradeoff scenarios.
-
Global PIQA: Physical Commonsense Reasoning Across 100+ Languages
By
–
5. Global PIQA Global PIQA extends physical commonsense reasoning evaluation to 100+ languages and cultural contexts, revealing how language models handle everyday practical scenarios across diverse linguistic communities.
-
SmolLM2: Strategic Data Curation Over Scale in Language Models
By
–
4. SmolLM2 SmolLM2 demonstrates that strategic data curation beats scale through a 1.7B parameter model trained on 11 trillion tokens using iterative data mixing optimization.
-
Multi-Agent Evolve: LLMs Self-Improve Without Human Annotation
By
–
3. Multi-Agent Evolve Multi-Agent Evolve (MAE) enables LLMs to self-improve their reasoning capabilities without human-annotated data through a co-evolving multi-agent framework.
-
LLMs Show Limited Introspective Awareness Capabilities
By
–
2. Introspective Awareness Anthropic research demonstrates that contemporary LLMs possess limited but functional introspective capabilities, the ability to recognize and accurately report on their own internal states.