While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query.
Flint is Recursive’s mixture-of-experts language model for coding agents, with 39.8 billion total parameters and approximately 2.5 billion active per token. It is designed to investigate codebases, fix bugs, implement features, and write tests.
China is pitching open-source artificial intelligence and a greater voice for the Global South as cornerstones for future tech regulations, ramping up efforts to challenge US dominance in setting rules for the rapidly evolving sector. The push was laid out in Global Governance:…
Product abuse is an individually rare, but growing, problem across the SaaS industry. Highly sophisticated threat actors can misuse security platforms within customer environments or conduct bypass experiments on the product itself. Threat actors can leverage…
Explainable Artificial Intelligence (XAI) has become essential in medical image analysis to ensure transparency of deep learning (DL)-based diagnostic systems. However, selecting appropriate XAI techniques for breast cancer recognition remains largely ad hoc, with limited…
Fairness research on language models involves measuring bias, applying mitigation methods, and examining the evidence on which an evaluation rests. Existing tools offer complementary functionality through different interfaces, so combining them requires reconciling model…
Autonomous software generation (ASG) aims to turn human requirements into executable applications, but delivering these applications does not necessarily establish that their interacting components satisfy the specified behavioral requirements. We introduce GameASG-Bench, a…