AI
ZenGen: Social Mind for LLMs
Researchers have developed ZenGen, an integrated framework for measuring and improving social intell...
AI
Prompt-Induced Waste in Coding Agents: Reasoning, Effort, Harness Design, and End-to-End Cost
Researchers have found that coding agents' efficiency cannot be measured solely by token count or mo...
AI
Tree-of-Experience: Hierarchical Experience Management for Self-Evolving Agents
Researchers propose a new framework for managing experiences in self-evolving agents. The Tree-of-Ex...
AI
Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model
Researchers have developed a new model called Factorized Inverse Decision Model (FIDM) to better und...
AI
Mint-Agent: Introducing Finance-Native Agentic Foundation Models
Researchers have developed a new family of AI models called Mint-Agent, designed...
AI
Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries
Large language models (LLMs) used in code generation often 'hallucinate', invent...
AI
LTR-ICD: A Ranking-Aware Framework for Automatic ICD Coding
Researchers have developed a new framework for automatically assigning and order...
AI
When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA
Researchers have investigated the effectiveness of knowledge distillation for CL...