AI
TL;DR Long-horizon LLM agents fail when one small error snowballs. Task-Decoupled Planning (TDP) breaks big jobs into a DAG of sub-goals, so planning and fixes stay local—making agents both sturdier and cheaper. How it works: * Supervisor decomposes the task into a directed acyclic graph of sub-goals. * Planner and
AI
Why chatbots forget—and how ES‑Mem fixes it Long chats often make assistants lose the thread. ES‑Mem, a new memory system, keeps conversations coherent by organizing them like humans do. * Breaks talks into “events.” Instead of saving every line, ES‑Mem detects natural boundaries—topics, goals, shifts—so
AI
What if AI could write many words at once, not just one after another? Diffusion LLMs can—yet they often trade speed for accuracy. Meet d3LLM, a new approach that keeps both. * Smarter training: Pseudo-trajectory distillation teaches the model which tokens are safe to finalize early, enabling confident parallel decoding.
AI
Reading Emotions from Text, Voice, and Video—Together Meet EGMF, a new AI that reads emotions by combining text, audio, and visuals. Instead of guessing from one signal, it fuses them all and adapts to context—working for both clear-cut emotions (like happy/sad) and nuanced sentiment on a scale.
AI
Ever wondered how words “talk” to each other inside AI? This study borrows a brain-scanning idea—diffusion tensor imaging (DTI)—to trace how information moves through word embeddings in large language models. Most visualizations plot single words as points, ignoring the context that gives language meaning. This new tool follows
AI
TL;DR Large language models can sound confident, but if you nudge the context, their beliefs can fall apart. This paper proposes a better way to check if an AI keeps its story straight. * Problem: Popular checks like self-consistency can hide brittle knowledge. Answers that look reliable vanish under mild
AI
Texting with AI can feel off—messages arrive in odd bursts with no real “thinking” pauses. Stephanie2 changes that. * Decides to send or wait: At every step, it chooses to message now or hold, like a human pausing to think. * Natural timing: It models delay as thinking time + typing time,
AI
New research shows that popular language models don’t persuade everyone the same way. Across 13 LLMs and 16 languages, the authors found consistent shifts in tone, appeals, and strategies depending on the recipient’s labeled gender — patterns that mirror well-known gender stereotypes. * Framework tests 19 categories of persuasive language
AI
AI agents powered by large language models can call tools, but they also hallucinate: picking the wrong tool, sending malformed parameters, or bypassing tools by simulating results. That breaks reliability, security, and audit trails in production. This study shows a lightweight way to catch those mistakes in real time. Instead
AI
AI meets messy spreadsheets New research shows that large language models (LLMs) struggle when tables are subtly distorted—through small layout or labeling tweaks—even if the data is otherwise standard. * LLMs rarely notice or fix these distortions on their own. * Giving an explicit "watch out for table errors&
AI
LLMs with Retrieval-Augmented Generation (RAG) work better when they read lots of context — but long prompts are slow and pricey. Compressing the context helps, yet models often lose the thread and answer worse. ArcAligner is a lightweight module that helps models make sense of highly compressed context. It "aligns&
AI
As AI models start learning from their own outputs, they risk entering an echo chamber. A new study names this cycle the Self-Consuming Performative Loop (SCPL) and shows how it can warp model behavior over time. * What’s the loop? Deployed models shape what people ask and which data gets