1). Automate Design of Agentic Systems – presents Meta Agent Search, a meta agent that iteratively programs and tests new agents based on a growing archive of previous discoveries; claims that with their approach it is possible to learn any possible agentic system including
@dair_ai
-
LLM Pruning and Distillation: Compressing Llama and Mistral Models
By
–
2). LLM Pruning and Distillation in Practice – provides a comprehensive report on effective methods for compressing Llama 3.1 and Mistral NeMo models; it presents pruning and distillation approaches applied to the original models to produce 4B and 8B parameter models,
-
Top ML Papers: GraphRAG, LLMs, Agents and Robustness
By
–
The Top ML Papers of the Week (August 19 – 25): – GraphRAG Methods
– LLMs for Tabular Data
– Automated Agentic Systems
– Enhancing Robustness in LLMs
– Controllable Text Generation for LLMs
– LLM Pruning and Distillation in Practice
… -
MedGraphRAG: Graph-Based Framework Enhancing LLMs Medical Domain
By
–
9/ MedGraphRAG – a graph-based framework for the medical domain with a focus on enhancing LLMs and generating evidence-based results; leverages a hybrid static-semantic approach to chunk documents to improve context capture; entities and medical knowledge are represented through
-
NL2SQL Techniques Survey: LLM Models and Evaluation Methods
By
–
10/ Survey of NL2QL – a comprehensive overview of NL2SQL techniques powered by LLMs; covers models, data collection, evaluation methods, and error analysis.
-
rStar Enhances Small Language Models Reasoning Without Fine-tuning
By
–
7/ rStar – introduces self-play mutual reasoning to improve the reasoning capabilities of small language models without fine-tuning or superior models; MCTS is augmented with human-like reasoning actions, obtained from SLMs, to build richer reasoning trajectories…
-
Optimal Scaling of LLM Inference-Time Compute
By
–
8/ Scaling LLM Test-Time Compute Optimally – investigates the scaling behaviors of inference-time computation in LLMs; in particular, it analyses how much an LLM can be improved provided a fixed amount of inference-time compute; finds that the effectiveness of different scaling
-
HybridRAG Combines GraphRAG VectorRAG for Superior Performance
By
–
6/ HybirdRAG – combines GraphRAG and VectorRAG leading to a HybridRAG system that outperforms both individually; it was tested on a set of financial earning call transcripts. Combining the advantages of both approaches provides more accurate answers to queries.
-
RAGChecker: Fine-Grained RAG Evaluation Framework
By
–
5/ RAGChecker – a fine-grained evaluation framework for diagnosing retrieval and generation modules in RAG; shows that RAGChecker has better correlations with human judgment; reports several revealing insightful patterns and trade-offs in design choices of RAG architectures.
-
LongWriter AgentWrite Enables LLMs Generate Beyond 20K Words
By
–
3/ LongWriter – proposes AgentWrite to enable off-the-shelf LLMs to generate coherent outputs beyond 20K words; AgentWrite breaks down the long generation task into subtasks and in a divide-and-conquer approach generates…