10/ LLM-based Multi-Agents – discusses the essential aspects of LLM-based multi-agent systems; it includes a summary of recent applications for problem-solving and word simulation; summarizes datasets, benchmarks, challenges, and future opportunities.
LLMS
-
Self-Discover: LLMs Select Reasoning Techniques for Tasks
By
–
7/ Self-Discovered Reasoning Structures – proposes a new framework, Self-Discover, that enables LLMs to select from multiple reasoning techniques (e.g., critical thinking and thinking step-by-step) to compose task-specific reasoning strategies.
-
DeepSeekMath Enhances Mathematical Reasoning with GRPO Optimization
By
–
8/ DeepSeekMath – continues pretraining a code base model with 120B math-related tokens; introduces GRPO (a variant to PPO) to enhance mathematical reasoning and reduce training resources via a memory usage optimization scheme.
-
LLMs for Table Processing: Methods, Benchmarks and Techniques
By
–
9/ LLMs for Table Processing – provides an overview of LLMs for table processing, including methods, benchmarks, prompting techniques, and much more.
-
Scaling LLM Agents Through Sampling and Voting Methods
By
–
6/ More Agents is All You Need – presents a study on the scaling property of raw agents instantiated by LLMs; finds that performance scales when increasing agents by simply using a sampling-and-voting method.
-
Indirect Reasoning Strengthens LLM Logical Reasoning Power
By
–
4/ Indirect Reasoning with LLMs – proposes an indirect reasoning method to strengthen the reasoning power of LLMs; it employs the logic of contrapositives and contradictions to tackle IR tasks such as factual reasoning and mathematic proof.
-
Phase Transition in Dot-Product Attention: Positional vs Semantic Learning
By
–
3/ A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention – studies the theoretical understanding of learning with attention layers by exploring the interplay between positional and semantic attention.
-
AnyTool: LLM Agent Framework for 16K API Integration
By
–
2/ AnyTool – an LLM-based agent that can utilize 16K APIs using a simple framework consisting of 1) a hierarchical API-retriever to identify relevant API candidates to a query, 2) a solver to resolve user queries, and 3) a self-reflection mechanism.
-
Speculation on upcoming GPT model features and updates
By
–
Not GPT 4.5 but rather – personalisation feature (proven)
– GPT ratings (proven)
– a new GPT 3 model with we browsing? -
Search ranking dynamics for custom GPTs
By
–
Hmm, actually by looking at “same creator boost 5” it feels like a search ranking. When you search for GPTs, yours always come first