Category
19,709 papers
Experiments show that LHM outperforms state-of-the-art methods such as ACM-TIES and ORCA, achieving over 4% accuracy gain and up to 93.1% reduction in output length relative to the long-CoT model.
El Agente F\'armaco, an AI scientist that uses modern large language model (LLM) technology to turn discovery goals expressed in everyday language into complex, scalable computational screening workflows, provides a foundation for flexible, scalable drug discovery workflows that connect scientific reasoning with an end...
This work identifies a novel phenomenon termed Ambient Context Illusion, where agents fail to execute tasks correctly when non-essential contextual details are omitted, despite unchanged task semantics, and demonstrates that this phenomenon persists in real-world robotic systems, where it can lead to incorrect decision...
The hypothesis that reasoning text has simpler co-occurrence topology than non-reasoning text is investigated, and that higher-quality reasoning has simpler co-occurrence topology than lower-quality reasoning is formulated.
Reach audiences
Advertise in front of researchers, engineers, and readers.
RAGLog is presented, which detects and localizes faults across RAG stages using execution logs, without requiring reference answers or code instrumentation, and is available as an open-source tool for debugging, evaluating, and monitoring RAG pipelines.
This work proposes EMBERS, an empirically motivated, defect-guided fuzzing framework for robustness testing of DR systems, and generates stage-targeted test inputs using defect-guided mutation, web-search-assisted fidelity assurance, and diversity-aware seed maintenance.
Simjecture, an open-source framework in which language-model agents pursue human-defined physical conjectures, is introduced to tackle the long-standing problem of radiated energy exceeding the imploding-shell kinetic energy in a Z-pinch and demonstrates a new paradigm for physics research.
Before a scientist fits any parameter, they must decide what the model contains: which quantities exist, which are hidden, how they interact, and how they are measured. Physicists call such a trial form an ansatz. Benchmarks for automated equation discovery mostly supply it, by fixing the variables, a library of candid...
This paper introduces RSI-Dojo, a collection of executable model training environments designed to teach LLM agents to conduct post-training, and develops RSI-Craft, an automatic pipeline that converts human research artifacts into executable model training environments.
This work introduces LOLPlay, a benchmark in native League of Legends with 36 champion-specific tasks spanning resource management, combat, cooperation, and objectives, and introduces GPT-6 Astra, a benchmark in real-time control with the highest task success rate at low and medium effort.
Language models serve as the reasoning core of agents for chemistry and materials science, where they must interpret molecular structure before planning syntheses or proposing materials. Yet their outputs show only what they say, not what they know. Given a prompt such as ``The primary functional group in 1-Fluorobutan...
MCPGuard is presented, an automated LLM-based framework for detecting specification-to-SDK conformance gaps and complements conventional endpoint-oriented conformance suites by making SDK conformance of specification constraints directly testable.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
