A new arXiv paper (2609.38958v1) reports that Chain-of-Thought reasoning improves long-context counting accuracy across twelve model comparison groups, with the largest gains at higher counts. The aut…
A new arXiv paper (2609.16589v1) reports that large language models possess an intrinsic value system, based on projecting responses from 106 LLMs at 150,000 queries per model and 95,000 human survey …
A developer argues that the era of verbose 'act as an expert' prompts is over, advocating for 'master prompts' as a stable policy layer above individual tasks. The piece details a structured framework…
Researchers introduced CreditCardQA, the first financial literacy benchmark for numerical reasoning derived from real credit card agreements, containing 1,800 questions. Evaluating large language and …
A new study, 'The Physics of Multi-Turn Long-Horizon Planning,' introduces a controlled environment to isolate variables in agentic planning. The research identifies three stages—pre-training, post-tr…
A developer introduced Program-Aided Language Models (PAL), which offload arithmetic from language models to a code interpreter. PAL splits reasoning and computation: the model writes a program descri…
Researchers released the official implementation of Graph of Thoughts (GoT), a framework that uses large language models to solve complex problems by modeling them as a Graph of Operations. The framew…
Researchers introduced VeryTrace, a zero-shot verification-and-repair framework that formalizes Chain-of-Thought reasoning traces into a compilable Domain-Specific Language, enabling step-level error …
Researchers introduced Reasoning Primitive Induction, a single-pass method that mines successful ReAct agent traces to extract recurrent reasoning moves into a compact library of typed pseudo-tools. T…
Researchers introduced ADHD, a method that fans out parallel divergent branches under different cognitive frames to prevent premature convergence in large language model agents. Across six open-ended …
Large language models (LLMs) show reduced accuracy on math problems when simple details like names or numbers are changed, and a new study finds that using code execution methods does not improve this…