Aug 7, 2026
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
HarnessOpt-Bench is a new benchmark designed to measure how well Large Language Models (LLMs) can perform "harness optimization"—the process of iteratively i...
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
Aug 7, 2026
DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
DASH (Divergence-Adaptive Supervision Horizons) is a method designed to improve how large language models learn reasoning tasks through on-policy self-distil...
Aug 7, 2026
Mind the Gaps: Mixture-of-Minds for Human Simulation
Mind the Gaps: Mixture-of-Minds for Human Simulation introduces Anacreon, a model designed to simulate individual human behavior within specific domains.
Aug 7, 2026
iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
iARCS is an iterative agentic reinforcement learning framework designed to improve the functional utility of synthetic 3D indoor scenes.
Aug 7, 2026
The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping
The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping investigates why current video-language models struggle to accurately count an...
Aug 7, 2026
Signal or Spurious Cue? A Randomized Audit of Survey-Country Metadata in LLM Social Inference
This paper investigates whether large language models (LLMs) distinguish between meaningful population data and arbitrary cues when predicting individual sur...
Aug 7, 2026
MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration
MicroEvo is a framework designed to optimize microarchitecture design space exploration (DSE) by combining the reasoning capabilities of Large Language Model...
Aug 7, 2026
The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images
The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images investigates why multimodal large language models (MLLMs) often fail to see performan...
Aug 7, 2026
Challenges in Evaluating Explanation Methods for Static and Evolving Data
Challenges in Evaluating Explanation Methods for Static and Evolving Data examines the current limitations in how researchers assess Explainable Artificial I...
Aug 7, 2026
Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI
Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI presents a framework for extracting complex, nested data from u...
Good to know
How do I use these AI research explainers?
Start with the overview to understand the paper’s main idea, then follow its original paper link for the methods, results and limitations.
Can I suggest a research paper?
Use Submit Research to send the original paper URL and explain why it is useful. An editor reviews the suggestion before publication.