936 stories tagged Research · page 16 of 39
Researchers created MA-ProofBench, the first formal theorem-proving benchmark dedicated to Mathematical Analysis. It could help develop smarter AI tutors and research assistants for complex math problems.
Researchers developed a Transformer-based AI model that solves the open shop scheduling problem (OSSP) faster and more efficiently, reducing the need for extensive tuning. Tested on Taillard benchmark instances (4x4, 5x5, 7x7, and 10x10), the approach could help businesses optimize production lines and reduce costs.
Researchers found that selecting training data can accidentally bias AI models, making them less accurate. This happens when the data used to verify the model is itself incomplete or skewed, leading to a breakdown in performance. This affects how AI systems learn and could impact everything from chatbots to medical diagnostics.
Researchers found that AI judges used to rank other AI models often change their minds when given the same question repeatedly. This inconsistency could affect how we measure AI performance and trust public leaderboards. The study tested two OpenAI judge models across 29 tasks and found that pairwise preferences flipped an average of 13.6% of the time, with 28% of questions exceeding a 20% flip rate. The findings highlight the need for more reliable evaluation methods.
Researchers created a new way to test AI lie detectors by using 13 reasoning 'model organisms' whose hidden beliefs are verified in chain-of-thought. This could improve how we audit and monitor AI systems in the future. The study highlights the importance of understanding what AI models truly believe versus what they say.
Researchers have introduced the Theory of Mind Utility (ToM-U), a formal mathematical framework that specifies how an AI system could infer others' beliefs by tracking who told them what, in what order, and how credible that information is. This is a theoretical model, not a built AI, and could guide future AI systems toward better understanding human social interactions.
Researchers have developed Pythagoras-Prover, a new family of AI models that can generate formal mathematical proofs efficiently. This advancement makes advanced theorem proving accessible with lower computational costs.
Researchers created an AI system that mimics human driving styles by conditioning on explicit human demonstrations. This could make driving simulations more realistic and safer.
Scientists found simple ways to ask AI models that make their judgments more stable and accurate. This could help AI give better advice on moral and social questions. The key is using the right prompts when asking the AI.
New research shows AI models' self-reported traits often don't match their actual behavior, but this may be due to weak testing methods—not incoherent AI. The study calls for more specific, context-matched psychometric probes to better predict AI actions in real-world deployments.
Researchers introduced ToolSense, a diagnostic framework for auditing parametric tool knowledge in LLMs. It helps AI agents select tools more accurately by encoding each tool as a virtual token and fine-tuning the model in two stages, outperforming traditional embedding-based retrieval on standard benchmarks.
Researchers developed a method to predict when AI assistants in healthcare might fail. This could make clinical AI tools safer and more reliable for doctors and patients. The study analyzed real-world use of AI in electronic health records to identify risky responses before they happen.
Researchers created an AI agent that can simulate human movement paths. This could help with city planning and disease tracking without needing real people's data.
A new research paper explores what comes after human-level AI, proposing a continuum from AGI to Universal AI. This could reshape society in ways we're only beginning to understand.
A new research paper introduces Evoflux, a method that helps compact AI agents create and adjust executable tool workflows during inference, rather than relying solely on pre-training data. This could make small models more reliable for MCP-style tasks.
Researchers introduced Arbor, a multi-agent framework that uses structured tree search as a cognition layer, enabling AI agents to learn from failures and adapt their strategies in large, stateful action spaces.
Researchers developed a system that converts complex scientific figures into narrated, region-grounded walkthrough videos. This could make scientific research more accessible to non-experts.
Researchers created AfriSUD, the first large-scale collection of syntactically annotated treebanks for nine diverse African languages, verified by native speakers. This is a major step toward making NLP more inclusive for millions of speakers across Sub-Saharan Africa.
A new research paper argues that AI needs explicit memory to reach human-like intelligence. This could change how we build and interact with AI in the future.
Scientists developed a new way to predict how AI systems will behave, bypassing traditional explanation methods. This could make AI more trustworthy by showing users what to expect.
Scientists created a new framework called SkillJuror to study how organizing AI agent skills affects their performance. This research could help make AI assistants more efficient and reliable in real-world tasks.
Researchers developed a system called INFRAMIND that improves AI performance by considering real-time hardware constraints. This could make AI tools faster and more efficient for everyday users.
Researchers developed a method called ACTION-RATING to help AI models ask for clarification when they're unsure. This could make AI assistants more reliable by reducing mistakes from guessing.
Researchers released SemantiClean, a modular AI framework that analyzes e-commerce session data to predict purchases and customer preferences. Unlike conventional AI, it prioritizes auditability and transparency over marginal gains in accuracy, providing a clear decision trail for every inference.