PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent
Explorar
Noticias de IA
30239 elementos — filtrados, clasificados y sin duplicados
CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents
Does the Competitive Component of Adversarial Self-Play Improve Legal Reasoning? A Contro…
LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Lay…
Computing with Agentic Oracles
Constructing Executable Analytical Knowledge Representations for Meta-Analysis Synthesis …
When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Perso…
DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion…
[AINews] Qwen 3.8 Max(2.4T) and 27B, new open weights models for Coding and Cowork
AI Security Leaderboard: Methodology, Results and Minimal Standard
CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dy…
SeqLLM: Augmenting LLMs with Behavioral-Sequence Modeling for High-Stakes Decisions at We…
AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coachi…
LLM Serving in the Wild: An Empirical Study of Frameworks, Methods, and System Designs
LoCA: Forward-Only LLM Tuning after One-Shot Calibration with Local Credit Assignment
Paired Recipient-based Evaluation of Survival Prediction for Deceased Donor Kidney Transp…
V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors
ProPRL: Property-Aware Prerequisite Relation Learning in Educational Knowledge Graphs
Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Pe…
On the Non-Specificity of Statistical Measures Used in Script Decipherment
NAB Tests AI Agents in Plan to Deploy Tech to Banking Customers
New ways to learn and teach with ChatGPT Work and Codex
ChronicleBio 🧬, Mind Lab continual learning 📈, GPT-Live architecture 🎙️
ATFlash: Per-RoPE-Wavelength Attention Windows for Compute/Memory-Efficient LLM Inference
After killer quarter, Palantir CEO Alex Karp calls AI industry ‘Marxist’
When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning
Interviewing Engineers in the AI Era: Lessons from a Year of Rebuilding
Did an AI Music App Just Snitch on the Song of the Summer?
FLARE: Few-shot Learning-based Adaptive Reflective Engine
Ukraine’s drones get AI upgrades for kamikaze strikes, future swarm attacks