Recent Research Signals

Found 45 results

Filtering papers...

Paper	Possible Impact	Features	Possible Business Area
Compliance Rating Scheme: A Data Provenance Framework for Generative AI Datasets Artificial Intelligence	Checks if AI training data is safe and fair.	Stanford University Code 2 Countries	Predictive Analytics (78%)	Score: 3 5 days ago
SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search Artificial Intelligence	Helps AI plan better by thinking, checking, and fixing mistakes.	IBM Code	Machine Learning (77%)	Score: 3 1 day ago
Monadic Context Engineering Artificial Intelligence	Builds stronger AI agents that handle mistakes better.	Princeton University Code	Machine Learning (80%)	Score: 2 3 days ago
CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations Artificial Intelligence	Helps robots understand and solve physical puzzles.	Princeton University 2 Countries	Artificial Intelligence (78%)	Score: 2 1 day ago
Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions Artificial Intelligence	Teaches robots to learn complex actions faster.	Code	Artificial Intelligence (77%)	Score: 2 6 days ago
LLM Agents as VC investors: Predicting Startup Success via RolePlay-Based Collective Simulation Artificial Intelligence	Helps predict which new companies will succeed.	2 Countries	Virtual World (80%)	Score: 1 3 days ago
Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback Artificial Intelligence	Teaches computers how the world works.		Simulation (80%)	Score: 1 4 days ago
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence Artificial Intelligence	Tests AI's smarts for science problems.	Code	Artificial Intelligence (82%)	Score: 1 4 days ago
Beyond Context: Large Language Models Failure to Grasp Users Intent Artificial Intelligence	AI models tricked by clever words.		Natural Language Processing (82%)	Score: 1 6 days ago
Accelerating Scientific Discovery with Autonomous Goal-evolving Agents Artificial Intelligence	Helps scientists invent new things by creating better goals.	University of California, Berkeley	Artificial Intelligence (83%)	Score: 1 5 days ago
Beyond Context: Large Language Models Failure to Grasp Users Intent Artificial Intelligence	Makes AI understand what you really mean.		Natural Language Processing (82%)	Score: 1 6 days ago
Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning Artificial Intelligence	Makes AI explain its choices and be trustworthy.	4 Countries	Artificial Intelligence (79%)	Score: 1 5 days ago
AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis Artificial Intelligence	AI writes code to make computer brains faster.	Huawei	Machine Learning (77%)	Score: 1 1 day ago
Three-way conflict analysis based on alliance and conflict functions Artificial Intelligence	Helps understand who is friends or enemies.	2 Countries	Artificial Intelligence (77%)	Score: 1 6 days ago
AMS-IO-Bench and AMS-IO-Agent: Benchmarking and Structured Reasoning for Analog and Mixed-Signal Integrated Circuit Input/Output Design Artificial Intelligence	Designs computer chips faster using smart language.	Code	Intelligent Systems (80%)	Score: 1 5 days ago
A Real-World Evaluation of LLM Medication Safety Reviews in NHS Primary Care Artificial Intelligence	AI helps doctors find medicine mistakes.		Natural Language Processing (79%)	Score: 1 6 days ago
TrafficSimAgent: A Hierarchical Agent Framework for Autonomous Traffic Simulation with MCP Control Artificial Intelligence	Helps plan traffic jams with simple words.		Autonomous Vehicles (79%)	Score: 1 6 days ago
LLM Personas as a Substitute for Field Experiments in Method Benchmarking Artificial Intelligence	Tests computer helpers without real people.	University of Washington	A/B Testing (79%)	Score: 1 6 days ago
LogicLens: Visual-Logical Co-Reasoning for Text-Centric Forgery Analysis Artificial Intelligence	Finds fake writing in pictures better.		Natural Language Processing (80%)	Score: 1 5 days ago
Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model Artificial Intelligence	Makes AI write shorter answers without losing quality.	Code	Natural Language Processing (76%)	Score: 1 5 days ago
MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs Artificial Intelligence	AI learns better by arguing with itself.	Code	Machine Learning (79%)	Score: 1 6 days ago
Feasible strategies in three-way conflict analysis with three-valued ratings Artificial Intelligence	Finds best ways to solve arguments between groups.		Artificial Intelligence (77%)	Score: 1 6 days ago
Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following Artificial Intelligence	Teaches AI to learn from its mistakes.	Alibaba	Machine Learning (76%)	Score: 1 1 day ago
Multimodal Fact-Checking: An Agent-based Approach Artificial Intelligence	Helps stop fake news with better computer checking.	Code	Natural Language Processing (78%)	Score: 1 2 days ago
Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients Artificial Intelligence	Helps AI understand X-rays better, but needs careful training.		Natural Language Processing (77%)	Score: 0 2 days ago
RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic Artificial Intelligence	Keeps robots from doing dangerous things.		Robotics (80%)	Score: 0 6 days ago
FinAgent: An Agentic AI Framework Integrating Personal Finance and Nutrition Planning Artificial Intelligence	Saves money on healthy food by watching prices.		Personal Finance (80%)	Score: 0 6 days ago
A Blockchain-Monitored Agentic AI Architecture for Trusted Perception-Reasoning-Action Pipelines Artificial Intelligence	Makes smart AI safe and trustworthy for important jobs.		Artificial Intelligence (81%)	Score: 0 6 days ago
Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation Artificial Intelligence	Makes AI explain farming advice better.		Machine Learning (82%)	Score: 0 6 days ago
Democratizing Drug Discovery with an Orchestrated, Knowledge-Driven Multi-Agent Team for User-Guided Therapeutic Design Artificial Intelligence	Finds new medicines faster by thinking like scientists.		Artificial Intelligence (80%)	Score: 0 5 days ago
The Silent Scholar Problem: A Probabilistic Framework for Breaking Epistemic Asymmetry in LLM Agents Artificial Intelligence	Agents learn faster by sharing what they don't know.		A/B Testing (77%)	Score: 0 6 days ago
RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic Artificial Intelligence	Keeps robots from doing dangerous things.		Robotics (80%)	Score: 0 6 days ago
Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks Artificial Intelligence	Makes computer brains smaller and faster.		Natural Language Processing (75%)	Score: 0 4 days ago
SpatialBench: Can Agents Analyze Real-World Spatial Biology Data? Artificial Intelligence	Helps computers understand cell maps for science.		Artificial Intelligence (80%)	Score: 0 4 days ago
Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing Artificial Intelligence	Helps computers share limited resources fairly and smartly.		A/B Testing (76%)	Score: 0 5 days ago
A Medical Multimodal Diagnostic Framework Integrating Vision-Language Models and Logic Tree Reasoning Artificial Intelligence	Helps AI doctors understand images and text better.		Natural Language Processing (80%)	Score: 0 5 days ago
NEMO-4-PAYPAL: Leveraging NVIDIA's Nemo Framework for empowering PayPal's Commerce Agent Artificial Intelligence	Makes online shopping faster and cheaper.		Natural Language Processing (78%)	Score: 0 5 days ago
Three-way decision with incomplete information based on similarity and satisfiability Artificial Intelligence	Helps computers make better choices with missing info.		Artificial Intelligence (79%)	Score: 0 6 days ago
Web World Models Artificial Intelligence	Lets AI explore and learn in many worlds.		Semantic Web (82%)	Score: 0 1 day ago
HiSciBench: A Hierarchical Multi-disciplinary Benchmark for Scientific Intelligence from Reading to Discovery Artificial Intelligence	Tests computers on science from reading to discovery.		Intelligent Systems (80%)	Score: 0 2 days ago
Memento-II: Learning by Stateful Reflective Memory Artificial Intelligence	Lets AI learn from past experiences without retraining.		Machine Learning (79%)	Score: 0 3 days ago
Learning Multi-Modal Mobility Dynamics for Generalized Next Location Recommendation Artificial Intelligence	Helps apps guess where you'll go next.		Navigation (79%)	Score: 0 3 days ago
Regret-Based Federated Causal Discovery with Unknown Interventions Artificial Intelligence	Finds hidden causes even with different data.		Predictive Analytics (76%)	Score: 0 1 day ago
Agentic Physical AI toward a Domain-Specific Foundation Model for Nuclear Reactor Control Artificial Intelligence	AI learns to control machines safely using physics.		Artificial Intelligence (80%)	Score: 0 1 day ago
InSPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization Artificial Intelligence	Teaches AI to learn better from comparing answers.		Natural Language Processing (76%)	Score: 0 1 day ago