Aug 25, 2026
Characterizing Necessary Losers to Explain Tournaments Losers
This paper addresses the challenge of explaining why a specific candidate loses an election when tournament rules are used to determine the winner.
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
Aug 25, 2026
ReWorld: An Interactive World Model with Long-Horizon Memory
ReWorld is an interactive world model designed to simulate environments that respond to user actions while maintaining long-term spatial memory.
Aug 25, 2026
Prime Agent: A Self-Improving RLM Harness
Prime Agent is an open-source harness designed to improve how language models handle long-horizon tasks, such as complex coding projects and autonomous resea...
Aug 25, 2026
Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation
Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation presents a system designed for the ACM RecSys 2026 Talk...
Aug 25, 2026
How AI Assistance Affects Human Skill Development: A Study of Learning with Logic Puzzles
How AI Assistance Affects Human Skill Development: A Study of Learning with Logic Puzzles investigates whether using AI to solve problems hinders a person's...
Aug 25, 2026
StrategyBench: Evaluating Explicit Strategy Induction in Large Language Models
StrategyBench is a new benchmark designed to evaluate how well large language models (LLMs) can "summarize before applying"—the ability to induce explicit, t...
Aug 25, 2026
EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards
EarthVerse is a benchmark designed to evaluate how well scientific AI agents can conduct complex, multi-source investigations into Earth-system events and na...
Aug 25, 2026
Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty
Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty addresses the problem of "Reasoning-Induced Misalignment" (RIM), where fine-tuning lar...
Aug 25, 2026
SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning introduces a framework that enables Large Language Models (LLMs) to improve their reason...
Aug 25, 2026
Correcting a learned physical invariant improves world-model rollouts
Correcting a learned physical invariant improves world-model rollouts investigates whether world models—AI systems designed to predict future video frames—ac...
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.