companyAngestromTrust 62Published 2mo agoLive · 2mo ago
Northwind AI
An applied-research lab building reliable reasoning models.
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownNew benchmark exposes reasoning gaps in top models →
- LinkedLinked via unknownSelf-rewarding agents that retrace failures →
- LinkedLinked via unknownLearning to lead in a hybrid human-AI enterprise →
- LinkedLinked via unknownkrushna081/chakravyuh-ai →
- LinkedLinked via unknownCORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs →
- LinkedLinked via unknownIntroducing LifeSciBench →
- LinkedLinked via unknownUsing AI to help physicians diagnose rare genetic diseases affecting children →
Covers
Related to
Related to (incoming)
paperCORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMspaperNuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language ModelsmodelRetrace-1.5Brepopisanuw/ltmspaperCOCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-NegativespaperCognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty PredictionpaperTravel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge GraphspaperMIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing CounselingpaperDynamo: Dynamic Skill-Tool Evolution for Vision-Language AgentspaperGrounding LLM Reasoning under Incomplete Graph EvidencepaperModality-Driven Search with Holistic Trace Judging for ARC-AGI-2paperAutomating Cause-Effect Specification with Knowledge Graphs and Large Language ModelspaperA Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM AgentspaperThink in English, Answer in Korean: Efficient Adaptation of Multilingual Tool-Using AgentspaperBridging the Gap Between Latent and Explicit Reasoning with Looped TransformerspaperGraph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual RecombinationpaperBayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question AnsweringpaperTheoria: Rewrite-Acceptability Verification over Informal Reasoning StatespaperAutonomous Scientific Discovery via Iterative Meta-ReflectionrepoUnpr3dictable/neurizon.airepoLabNow-ai/lab-foundationreposemantica-agi/semanticarepospring-projects/spring-aireposileod/reasoning-corerepobenjaminzwhite/reasoning-modelspaperTUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27BpaperCheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoningrepoa-Fig/Accordionrepobonigarcia/context-engineeringrepopancsta/secairepoTHU-Team-Eureka/EurekAgentreponoetheadynamics/alethearepojohnsonfarmsus/openwebui-ab-mcts-pipelinepaperRing-Zero: Scaling Zero RL to a Trillion Parameters for Emergent ReasoningpaperAIMO Interpretability ChallengepaperDeep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning ModelspaperCoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QApaperFrom Plausible to Actionable: A Position on LLM Self-ExplanationspaperA Method for Learning Value Systems in Generative AIpaperDebate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge GraphpaperPoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity
Covers (incoming)
newsIntroducing LifeSciBenchnewsUsing AI to help physicians diagnose rare genetic diseases affecting childrennewsReflections on Software Engineering in the Age of AInewsChain-of-Thought Spoofing Targets Reasoning AI Models - HackadaynewsNemotron Labs: How Open Models Give Enterprises and Nations AI They Can Trust, Control and Customize
Related across the graph
paperDebate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge GraphpaperCheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented ReasoningpaperDynamo: Dynamic Skill-Tool Evolution for Vision-Language AgentsnewsNemotron Labs: How Open Models Give Enterprises and Nations AI They Can Trust, Control and CustomizepaperCOCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-NegativesnewsLearning to lead in a hybrid human-AI enterprisereponoetheadynamics/alethearepoTHU-Team-Eureka/EurekAgentpaperA Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM AgentspaperMIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing CounselingpaperSelf-rewarding agents that retrace failuresreposemantica-agi/semanticarepobonigarcia/context-engineeringrepoUnpr3dictable/neurizon.aipaperGrounding LLM Reasoning under Incomplete Graph EvidencepaperAIMO Interpretability ChallengepaperBayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question AnsweringpaperDeep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Modelsrepoa-Fig/Accordionrepopancsta/secainewsUsing AI to help physicians diagnose rare genetic diseases affecting childrenpaperAutonomous Scientific Discovery via Iterative Meta-Reflectionrepobenjaminzwhite/reasoning-modelspaperPoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneityrepokrushna081/chakravyuh-aipaperTravel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge GraphsnewsIntroducing LifeSciBenchrepospring-projects/spring-airepopisanuw/ltmsnewsChain-of-Thought Spoofing Targets Reasoning AI Models - Hackadayrepojohnsonfarmsus/openwebui-ab-mcts-pipelinepaperThink in English, Answer in Korean: Efficient Adaptation of Multilingual Tool-Using AgentspaperRing-Zero: Scaling Zero RL to a Trillion Parameters for Emergent ReasoningmodelRetrace-1.5BpaperFrom Plausible to Actionable: A Position on LLM Self-Explanationsreposileod/reasoning-corepaperTheoria: Rewrite-Acceptability Verification over Informal Reasoning StatespaperCORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMspaperModality-Driven Search with Holistic Trace Judging for ARC-AGI-2paperTUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27BrepoLabNow-ai/lab-foundationpaperBridging the Gap Between Latent and Explicit Reasoning with Looped TransformerspaperCoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QApaperAutomating Cause-Effect Specification with Knowledge Graphs and Large Language ModelsnewsNew benchmark exposes reasoning gaps in top modelspaperNuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language ModelspaperA Method for Learning Value Systems in Generative AIpaperCognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty PredictionpaperGraph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual RecombinationnewsReflections on Software Engineering in the Age of AI