AI
From Contexts to Values: Context-Dependent Defeat in Abstract Argumentation
Researchers have developed context-dependent argumentation frameworks (CDAFs), which allow for diffe...
AI
ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search
Researchers have developed a new algorithm called ATLAS that allows large language models (LLMs) to ...
AI
Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling
Researchers propose AdmitOR, a label-free admission mechanism for optimization modeling that uses ca...
AI
From Generalist to Specialist: A Context-Fusion Framework for Endoscopic Polyp Reporting with a Frozen VLM
Researchers have developed a context-fusion framework to improve the accuracy of endoscopic polyp re...
AI
Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback
Researchers have developed Agent Gym, a framework designed to continuously evalu...
AI
When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction
Researchers have developed a new framework called ESTP (Entropy-and-Semantic Tok...
AI
TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation
Researchers have developed a new defense system called TRACE to protect large la...
AI
VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation
Researchers have introduced a new benchmark called VARM-Bench to evaluate the pe...