From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents
An AI research paper on From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
aipentium - AI Papers with Code, Datasets and Engineering Notes
aipentium: browse curated AI and robotics papers about humanoid robots, embodied AI, robot manipulation, VLA models, Diffusion Policy, Sim2Real and robot foundation models.
PLURAL: A Global Dataset for Value Alignment
An AI research paper on PLURAL: A Global Dataset for Value Alignment.
Engineering 5.0 · Research 7.0 · Business 4.0
A safety-oriented hypothetico-deductive framework for AI-assisted differential diagnosis
An AI research paper on A safety-oriented hypothetico-deductive framework for AI-assisted differential diagnosis.
Engineering 5.0 · Research 7.0 · Business 4.0
What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness
An AI research paper on What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness.
Engineering 5.0 · Research 7.0 · Business 4.0
Who Analyses the Analyser? Self-Validating LLM Hazard Analysis with Constitutional Meta-STPA
An AI research paper on Who Analyses the Analyser? Self-Validating LLM Hazard Analysis with Constitutional Meta-STPA.
Engineering 5.0 · Research 7.0 · Business 4.0
Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization
An AI research paper on Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization.
Engineering 5.0 · Research 7.0 · Business 4.0
CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
An AI research paper on CausalDS: Benchmarking Causal Reasoning in Data-Science Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents
An AI research paper on ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents.
Engineering 5.0 · Research 7.0 · Business 4.0
Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
An AI research paper on Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets.
Engineering 5.0 · Research 7.0 · Business 4.0
A First-Principles Theory of Slow Thinking and Active Perception
An AI research paper on A First-Principles Theory of Slow Thinking and Active Perception.
Engineering 5.0 · Research 7.0 · Business 4.0
Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation
An AI research paper on Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation.
Engineering 5.0 · Research 7.0 · Business 4.0
MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters
An AI research paper on MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters.
Engineering 5.0 · Research 7.0 · Business 4.0
Multi-Agent Firewall Architecture for Privacy Protection of Sensitive Data in Interactions with Language Models
An AI research paper on Multi-Agent Firewall Architecture for Privacy Protection of Sensitive Data in Interactions with Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench
An AI research paper on Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench.
Engineering 5.0 · Research 7.0 · Business 4.0
WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving
An AI research paper on WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving.
Engineering 5.0 · Research 7.0 · Business 4.0
Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination
An AI research paper on Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination.
Engineering 5.0 · Research 7.0 · Business 4.0
OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice
An AI research paper on OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice.
Engineering 5.0 · Research 7.0 · Business 4.0
DocMaster: A Hierarchical Structure-Aware System for Document Analysis
An AI research paper on DocMaster: A Hierarchical Structure-Aware System for Document Analysis.
Engineering 5.0 · Research 7.0 · Business 4.0
VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval
An AI research paper on VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval.
Engineering 5.0 · Research 7.0 · Business 4.0
Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance
An AI research paper on Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance.
Engineering 5.0 · Research 7.0 · Business 4.0