Northwind AI
An applied-research lab building reliable reasoning models.
Papers · 28
Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph
Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning. Nevertheless, KGs often contain noise and errors, while existing KG-enhanced LLM approaches are generally unable to identify and filter such noisy and erroneous content, which can instead amplify hallucinations and pose challenges for reliable reasoning. Uncertain knowledge g
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are prone to containing factual errors, particularly in knowledge-intensive tasks. To address this issue, we propose CheckRLM, a framework that improves the reliability of the reasoning process through Retrieval-Augmented Generation (RAG) by timely checking and correcting factual errors. Specifically, CheckRLM extracts factual claims from the reasoning chain to identify and localize subtle knowledge inconsistencies during inference. Upon detection of
Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents
Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools. We present Dynamo, a training-free framework that adapts a frozen VLM without any weight updates. On a small labeled training subset, the agent inspects its own correct and incorrect attempts and evolves two complementary capabilities: reusable reasoning skills for cognitive bottlenecks, and executable visual tools for perceptual ones. Each generated tool is paired with a skill that specifies when to invoke it, and both capability types accumulate in a persistent librar
COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives
While interpretable models such as concept bottleneck models (CBMs) and program synthesis methods enable verification of model decisions, their evaluation is typically limited to simple tasks, leaving complex reasoning on real-world images largely unexplored. We introduce COCOLogic-V2, an object-centric dataset for visual inductive reasoning on real-world images covering a broad subset of first-order logic. By categorizing samples into positive variants, near-boundary (NB), and far-from-boundary (FB) negatives, COCOLogic-V2 enables fine-grained diagnosis of model accountability. Our evaluation
A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents
Fault recovery in process plants still relies heavily on plant operators, especially when faults fall outside predefined supervisory logic. Operators interpret alarms, procedures, P\&IDs, interlocks, and process trends, then decide how to move the plant to a safe operating mode without triggering a shutdown. This paper examines how Large Language Model (LLM) agents can support such recovery decisions. The proposed framework treats the LLM as a constrained supervisory planner. It uses plant-specific knowledge to propose recovery actions, and every proposal is checked by an external validator (s
MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing Counseling
Reasoning large language models (LLMs) have recently made much progress in complex problem-solving, leveraging internal reasoning (or thought) to guide their solution generation. However, existing LLM-based counseling agents, including those using Motivational Interviewing (MI), generate responses without explicitly aligning thoughts with counseling techniques, limiting their effectiveness. We propose MIThinker, a lightweight thinking model that generates therapeutic thoughts to guide MI counseling agents in strategy selection and response generation. To overcome the lack of annotated thought
Self-rewarding agents that retrace failures
Agents that attribute their own errors and retrace to repair multi-step reasoning.
Grounding LLM Reasoning under Incomplete Graph Evidence
Knowledge graphs can guide large language models (LLMs) reasoning, but the graph seen by a system is usually a retrieved, linked, temporally scoped, and incomplete evidence state rather than a complete account of truth. We develop a theoretical perspective on grounding observable LLM trajectories under such incomplete graph evidence.The evidence state induces entity anchors, typed relation residuals, path energies, and support regions, while the language model supplies a prior over candidate trajectories. We show that, under open-world incompleteness, no hard rule based only on the observed st
News · 7
Nemotron Labs: How Open Models Give Enterprises and Nations AI They Can Trust, Control and Customize
Enterprises have plenty of powerful models to choose from. The real test is whether the AI an enterprise builds uniquely addresses the needs of the business: improving workflows, tapping into domain knowledge and exceeding standards for accuracy and trust.
Learning to lead in a hybrid human-AI enterprise
As adoption of AI agents looks set to surge by as much as 300% in the next two years, leadership teams are carefully considering the implications of a hybrid human-AI workforce. Unlike existing enterprise-level automation that relies on manual input, AI agents are capable of autonomously coordinating complex tasks, interacting with multiple tools and environments across…
Using AI to help physicians diagnose rare genetic diseases affecting children
Researchers used an OpenAI reasoning model to help diagnose rare diseases, identifying 18 new diagnoses in previously unsolved cases.
Introducing LifeSciBench
Introducing LifeSciBench, an expert-authored, expert-reviewed benchmark for evaluating how AI systems handle real-world life science research tasks and decisions.
Chain-of-Thought Spoofing Targets Reasoning AI Models - Hackaday
<a href="https://news.google.com/rss/articles/CBMijwFBVV95cUxNSzRpQjV6c2xVZzZnaW9DVGstNXFYUUlFV2dZc0hBWWFmT0lnNVFSQm9UWDdQYmxYbHJDVmJMTHlpT3EwaTQ1dV9FRGVsWEVTaEVVOGIweTYzdFpuLXp2QzFfTEdXU3ZENVFqczgtckFzR2dGYkZSbEs0V2I1Q2wyUWJqS2VBNGt1UEluN2J6TQ?oc=5" target="_blank">Chain-of-Thought Spoofing Targets Reasoning AI Models</a> <font color="#6f6f6f">Hackaday</font>
New benchmark exposes reasoning gaps in top models
A harder evaluation suite shows even leading models struggle on multi-hop tasks.
Reflections on Software Engineering in the Age of AI
<p>Article URL: <a href="https://adiamond.me/2026/06/software-engineering-in-the-age-of-ai/">https://adiamond.me/2026/06/software-engineering-in-the-age-of-ai/</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=48708721">https://news.ycombinator.com/item?id=48708721</a></p> <p>Points: 62</p> <p># Comments: 30</p>
Repositories · 14
noetheadynamics/alethea
A model-agnostic agentic LLM system built on Retrieval-First Reasoning Architecture (RFRA). Zero hallucination by design. Works with any OpenAI-compatible API or local model. https://alethea-noethea-ai.netlify.app
THU-Team-Eureka/EurekAgent
EurekAgent: an autonomous research system for metric-driven tasks, built with Claude Code. Define the problem and metric. Get breakthrough results.
semantica-agi/semantica
Graph-Native Infrastructure for Context and Accountable AI Systems
bonigarcia/context-engineering
Context Engineering: Build Consistent, Accurate, Predictable AI Systems
Unpr3dictable/neurizon.ai
The Neurizon Systems Artificial Intelligence
a-Fig/Accordion
🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers
pancsta/secai
Reasoning AI Workflows (devtools included)
benjaminzwhite/reasoning-models
Experiments with reasoning models, training techniques, papers