Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…

automated reasoning

30 articles about automated reasoning in AI news

New AI Benchmark Exposes Critical Gap in Causal Reasoning: Why LLMs Struggle with Real-World Research Design

Researchers have introduced CausalReasoningBenchmark, a novel evaluation framework that separates causal identification from estimation. The benchmark reveals that while LLMs can identify high-level strategies 84% of the time, they correctly specify full research designs only 30% of the time, highlighting a critical bottleneck in automated causal inference.

70% relevant

NVIDIA's Audio Flamingo Next: 30-Min Audio, Time-Grounded Reasoning

NVIDIA has launched Audio Flamingo Next, a next-generation open audio-language model supporting 30-minute audio inputs and time-grounded reasoning. Trained on over 1 million hours of data, it reportedly outperforms larger models on key audio understanding benchmarks.

95% relevant

Microsoft's MEMENTO Method Reduces LLM Reasoning Memory by 3x

Microsoft researchers introduced MEMENTO, a method where LLMs generate structured 'notes' during multi-step reasoning, reducing the memory footprint of the reasoning process by 3x while maintaining performance. This addresses a key bottleneck in deploying complex reasoning models.

80% relevant

OpenAI Reallocates Compute and Talent Toward 'Automated Researchers' and Agent Systems

OpenAI is reallocating significant compute resources and engineering talent toward developing 'automated researchers' and agent-based systems capable of executing complex tasks end-to-end, signaling a strategic pivot away from some existing projects.

89% relevant

Study Finds LLM 'Brain Activity' Collapses Under Hard Questions, Revealing Internal Reasoning Limits

New research shows language models' internal activation patterns shrink and simplify when faced with difficult reasoning tasks, suggesting they may rely on shortcuts rather than deep reasoning. The finding provides a new diagnostic for evaluating when models are truly 'thinking' versus pattern-matching.

85% relevant

ViGoR-Bench Exposes 'Logical Desert' in SOTA Visual AI: 20+ Models Fail Physical, Causal Reasoning Tasks

Researchers introduce ViGoR-Bench, a unified benchmark testing visual generative models on physical, causal, and spatial reasoning. It reveals significant deficits in over 20 leading models, challenging the 'performance mirage' of current evaluations.

94% relevant

New 'Step-by-Step Feedback' Reward Model Trains AI Agents to Fix Reasoning Errors

Researchers introduce a reward model that provides granular, step-by-step feedback to AI agents during training, helping them identify and correct reasoning errors. The approach aims to improve agent performance on complex, multi-step tasks.

85% relevant

LLMs Score Only 22% Win Rate in Multi-Agent Clue Game, Revealing Deductive Reasoning Gaps

Researchers created a text-based Clue game to test LLM agents' multi-step deductive reasoning. Across 18 games with GPT-4o-mini and Gemini-2.5-Flash agents, only 4 correct wins were achieved, showing fine-tuning on logic puzzles doesn't reliably improve performance.

75% relevant

The Power of Simplicity: How Minimalist AI Agents Are Revolutionizing Automated Theorem Proving

New research challenges the prevailing wisdom that complex AI systems are necessary for sophisticated tasks like automated theorem proving. A deliberately minimalist agent architecture demonstrates that streamlined approaches can achieve competitive performance while improving reproducibility and efficiency.

85% relevant

AI Research Breakthroughs: From Video Reasoning to Self-Stopping Models

This week's top AI papers reveal major advances in video understanding, reasoning efficiency, and agent training. Researchers introduced a massive video reasoning dataset, models that know when to stop thinking, and techniques for improving AI agents without full retraining.

95% relevant

Nano Banana 2: How AI's Latest Leap in Complex Reasoning Could Transform Everyday Tasks

OpenAI's latest model iteration, nicknamed 'Nano Banana 2,' demonstrates significant improvements in handling complex, multi-step reasoning tasks with greater speed and accuracy, particularly in understanding detailed instructions and nuanced contexts.

85% relevant

Research: Cheaper Reasoning Models Can Cost 3x More Due to Higher Error Rates and Retry Loops

New research indicates that selecting AI models based solely on per-token pricing can be a false economy. Models with lower accuracy often require multiple expensive retries, ultimately increasing total costs by up to 300%.

87% relevant

DiffGraph: An Agent-Driven Graph Framework for Automated Merging of Online Text-to-Image Expert Models

Researchers propose DiffGraph, a framework that automatically organizes and merges specialized online text-to-image models into a scalable graph. It dynamically activates subgraphs based on user prompts to combine expert capabilities without manual intervention.

95% relevant

How Semantic AI Bridges Threat Intelligence to Automated Firewall Defense

Researchers propose a neuro-symbolic AI system that automatically converts cyber threat intelligence into firewall rules using semantic relationships. The approach leverages hypernym-hyponym relations to extract actionable security information, outperforming traditional methods.

75% relevant

Anthropic CEO Dario Amodei Predicts 50% of Entry-Level White-Collar Jobs Could Be Automated Within 3 Years

Anthropic CEO Dario Amodei stated in an interview that AI could automate 50% of entry-level white-collar jobs within three years. The prediction highlights the rapid timeline some industry leaders anticipate for AI's impact on knowledge work.

85% relevant

HyEvo Framework Automates Hybrid LLM-Code Workflows, Cuts Inference Cost 19x vs. SOTA

Researchers propose HyEvo, an automated framework that generates agentic workflows combining LLM nodes for reasoning with deterministic code nodes for execution. It reduces inference cost by up to 19x and latency by 16x while outperforming existing methods on reasoning benchmarks.

95% relevant

HAVEN Benchmark Exposes MLLM Gap Between Fluency and Video Understanding

HAVEN benchmark tests MLLMs on hierarchical video understanding across frame, shot, and video levels. Results show top models lack grounded multimodal reasoning despite fluent text generation.

85% relevant

Google's Design.md Gives AI Coding Agents a Visual Design Memory

Google introduced Design.md, a file format for storing design tokens and rules that AI coding agents can read to maintain visual consistency, addressing a key failure point in automated UI generation.

95% relevant

Omar Sar Uses Opus 4.7 Agent to Turn Podcasts into Self-Improving Wikis

AI researcher Omar Sar automated podcast consumption using an Opus 4.7 agent that extracts insights, generates analysis, and builds interactive HTML/JS artifacts. The system creates a self-improving knowledge wiki for agentic research workflows.

87% relevant

BERT-as-a-Judge Matches LLM-as-a-Judge Performance at Fraction of Cost

Researchers propose 'BERT-as-a-Judge,' a lightweight evaluation method that matches the performance of costly LLM-as-a-Judge setups. This could drastically reduce the cost of automated LLM evaluation pipelines.

85% relevant

Correct Chains, Wrong Answers

A new benchmark called the Novel Operator Test reveals that large language models can perform every step of logical reasoning correctly yet still declare the wrong final answer. This dissociation between reasoning process and output accuracy challenges assumptions about LLM reliability for complex tasks.

74% relevant

AI System Re-Identifies 67% of Anonymous Users from Text for $4 Each

Researchers combined GPT-5.2, Gemini, and Grok 4.1 Fast to create an automated attack that links anonymous social media accounts to real identities with 67% accuracy at 90% precision, costing just $1-4 per identification.

95% relevant

AI Researcher Automates Slide Decks from 1K+ Paper Wiki Using Gamma MCP

Omar S. automated the creation of slide presentations from a personal wiki of 1,000+ AI papers. The pipeline uses the Gamma MCP connector for Claude to generate polished decks on demand.

75% relevant

FashionStylist: New Expert-Annotated Dataset Aims to Unify Multimodal

A new arXiv preprint introduces FashionStylist, a dataset with professional fashion annotations for item grounding, outfit completion, and outfit evaluation. It aims to address the fragmentation in existing fashion AI benchmarks by providing expert-level reasoning data.

86% relevant

OpenAI Solves Five Erdős Problems with Internal AI Model

OpenAI researchers have reportedly solved five additional unsolved Erdős problems using an internal AI model. This demonstrates significant progress in AI's ability to tackle complex, open-ended mathematical reasoning.

95% relevant

Alibaba's VulnSage Generates 146 Zero-Days via Multi-Agent Exploit Workflow

Alibaba researchers published VulnSage, a multi-agent LLM framework that generates functional software exploits. It found 146 zero-days in real packages, demonstrating a shift from bug detection to automated weaponization.

99% relevant

Meta-Harness from Stanford/MIT Shows System Code Creates 6x AI Performance Gap

Stanford and MIT researchers show AI performance depends as much on the surrounding system code (the 'harness') as the model itself. Their Meta-Harness framework automatically improves this code, yielding significant gains in reasoning and classification tasks.

95% relevant

ASI-Evolve Automates AI Research Loop, Discovers 105 Better Linear Attention Designs and Boosts AMC32 Scores by 12.5 Points

Researchers developed ASI-Evolve, an AI system that automates experimental loops in AI research. It discovered 105 improved linear attention variants and boosted AMC32 scores by 12.5 points, demonstrating automated research acceleration.

95% relevant

CMU Research Identifies 'Biggest Unlock' for Coding Agents: Strategic Test Execution

New research from Carnegie Mellon University suggests the key advancement for AI coding agents lies not in raw code generation, but in developing strategies for how to run and interpret tests. This shifts focus from LLM capability to agentic reasoning.

87% relevant

Fine-Tuning LLMs While You Sleep: How Autoresearch and Red Hat Training Hub Outperformed the HINT3 Benchmark

Automated fine-tuning tools now let you run hundreds of training experiments overnight for under $50. Here's how Autoresearch and Red Hat's platform outperformed HINT3, and the tools you can use today.

95% relevant