Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activ…
LiPUP-MA: A Residential Experience-centric Multi-Agent Framework for Living-in-the-loop P…
Risk Averse Alert Prioritization for IDS Using Subnormal Gaussian Fuzzy Models
Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)
Many Logics, One Methodology: A Plea for Logical Pluralism in Formalised Reasoning (prepr…
Algebraic Semantics of Governed Execution: Monoidal Categories, Effect Algebras, and Cote…
Mechanized Foundations of Structural Governance: Machine-Checked Proofs for Governed Inte…
Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents
MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chain…
Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling
Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Dat…
Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection
Yes, Q-learning Helps Offline In-Context RL
UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution
Generative Animations: A Multi-Model Pipeline for Prompt-Driven Motion Synthesis
Phase-Type Variational Autoencoders for Heavy-Tailed Data
Beyond Questions: Evaluating What Large Language Models (Actually) Know
MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Mo…
MobileExplorer: Accelerating On-Device Inference for Mobile GUI Agents via Online Explora…
VesselSim: learning 3D blood vessel segmentation without expert annotations
CmIVTP: Cross-modal Interaction-based Vessel Trajectory Prediction for Maritime Intellige…
On the Push-Based Asynchronous Federated Learning: A Bias-Correction Aggregation Approach
ORLoopBench: Solver-in-the-Loop Benchmarks for Self-Correction and Behavioral Rationality…
AgentAtlas: Beyond Outcome Leaderboards for LLM Agents
CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessme…
TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models
Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL