TikTok Researchers Introduce SWE-Perf: The First Benchmark for Repository-Level Code Performance Optimization
Source: MarkTechPost Introduction As large language models (LLMs) advance in software engineering tasks—ranging from code generation to bug...
Allen Institute for AI-Ai2 Unveils AutoDS: A Bayesian Surprise-Driven Engine for Open-Ended Scientific Discovery
Source: MarkTechPost The Allen Institute for Artificial Intelligence (AI2) has introduced AutoDS (Autonomous Discovery via Surprisal), a groundbreaking...
MIRIX: A Modular Multi-Agent Memory System for Enhanced Long-Term Reasoning and Personalization in LLM-Based Agents
Source: MarkTechPost Recent developments in LLM agents have largely focused on enhancing capabilities in complex task execution. However,...
Can LLM Reward Models Be Trusted? Master-RM Exposes and Fixes Their Weaknesses
Source: MarkTechPost Generative reward models, where large language models (LLMs) serve as evaluators, are gaining prominence in reinforcement...
NVIDIA AI Releases OpenReasoning-Nemotron: A Suite of Reasoning-Enhanced LLMs Distilled from DeepSeek R1 0528
Source: MarkTechPost NVIDIA AI has introduced OpenReasoning-Nemotron, a family of large language models (LLMs) designed to excel in...
MemAgent: A Reinforcement Learning Framework Redefining Long-Context Processing in LLMs
Source: MarkTechPost Handling extremely long documents remains a persistent challenge for large language models (LLMs). Even with techniques...
This AI Paper Introduces ARAG: A Multi-Agent RAG Framework for Context-Aware and Personalized Recommendations
Source: MarkTechPost Personalized recommendations have become a vital component of many digital systems, aiming to surface content, products,...
EG-CFG: Enhancing Code Generation with Real-Time Execution Feedback
Source: MarkTechPost LLMs have made impressive strides in generating code for various programming tasks. However, they mostly rely...
AegisLLM: Scaling LLM Security Through Adaptive Multi-Agent Systems at Inference Time
Source: MarkTechPost The Growing Threat Landscape for LLMs LLMs are key targets for fast-evolving attacks, including prompt injection,...
GLM-4.1V-Thinking: Advancing General-Purpose Multimodal Understanding and Reasoning
Source: MarkTechPost Vision-language models (VLMs) play a crucial role in today’s intelligent systems by enabling a detailed understanding...