惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

T
Tenable Blog
K
Kaspersky official blog
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
T
The Exploit Database - CXSecurity.com
Cisco Talos Blog
Cisco Talos Blog
P
Palo Alto Networks Blog
Latest news
Latest news
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
C
CXSECURITY Database RSS Feed - CXSecurity.com
P
Privacy International News Feed
The Hacker News
The Hacker News
T
Tor Project blog
www.infosecurity-magazine.com
www.infosecurity-magazine.com
C
Cisco Blogs
阮一峰的网络日志
阮一峰的网络日志
Recent Commits to openclaw:main
Recent Commits to openclaw:main
博
博客园_首页
N
News and Events Feed by Topic
W
WeLiveSecurity
罗
罗磊的独立博客
GbyAI
GbyAI
T
Troy Hunt's Blog
Y
Y Combinator Blog
Recorded Future
Recorded Future
The Cloudflare Blog
TaoSecurity Blog
TaoSecurity Blog
爱范儿
爱范儿
美
美团技术团队
Attack and Defense Labs
Attack and Defense Labs
C
Check Point Blog
Engineering at Meta
Engineering at Meta
Cyberwarzone
Cyberwarzone
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
F
Fortinet All Blogs
The GitHub Blog
The GitHub Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Apple Machine Learning Research
Apple Machine Learning Research
Know Your Adversary
Know Your Adversary
AWS News Blog
AWS News Blog
D
DataBreaches.Net
Recent Announcements
Recent Announcements
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
M
MIT News - Artificial intelligence
Webroot Blog
Webroot Blog
Security Latest
Security Latest
T
Tailwind CSS Blog
V2EX - 技术
V2EX - 技术
aimingoo的专栏
aimingoo的专栏
S
Security @ Cisco Blogs
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed

cs.AI updates on arXiv.org

Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-Tuning Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method CocoaBench: Evaluating Unified Digital Agents in the Wild MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis Efficient Training for Cross-lingual Speech Language Models Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities Uncertainty-Aware Web-Conditioned Scientific Fact-Checking When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies When Verification Fails: How Compositionally Infeasible Claims Escape Rejection Mem$^2$Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation AOP-Smart: A RAG-Enhanced Large Language Model Framework for Adverse Outcome Pathway Analysis Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series TInR: Exploring Tool-Internalized Reasoning in Large Language Models Do BERT Embeddings Encode Narrative Dimensions? A Token-Level Probing Analysis of Time, Space, Causality, and Character in Fiction Generating Multiple-Choice Knowledge Questions with Interpretable Difficulty Estimation using Knowledge Graphs and Large Language Models Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models Learning and Enforcing Context-Sensitive Control for LLMs Efficient Process Reward Modeling via Contrastive Mutual Information Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models LLMs Should Incorporate Explicit Mechanisms for Human Empathy ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities CircuitSynth: Reliable Synthetic Data Generation ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models Computational Implementation of a Model of Category-Theoretic Metaphor Comprehension CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models Should We be Pedantic About Reasoning Errors in Machine Translation? GIANTS: Generative Insight Anticipation from Scientific Literature SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning Many-Tier Instruction Hierarchy in LLM Agents Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories PhysInOne: Visual Physics Learning and Reasoning in One Suite Neural Distribution Prior for LiDAR Out-of-Distribution Detection Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition PDE-regularized Dynamics-informed Diffusion with Uncertainty-aware Filtering for Long-Horizon Dynamics Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection Regime-Conditional Retrieval: Theory and a Transferable Router for Two-Hop QA Identification and Anonymization of Named Entities in Unstructured Information Sources for Use in Social Engineering Detection Hypergraph Neural Networks Accelerate MUS Enumeration ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learning Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems WOMBET: World Model-Based Experience Transfer for Robust and Sample-efficient Reinforcement Learning Adaptive Dual Residual U-Net with Attention Gate and Multiscale Spatial Attention Mechanisms (ADRUwAMS) Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective A Mathematical Framework for Temporal Modeling and Counterfactual Policy Simulation of Student Dropout Temporal Dropout Risk in Learning Analytics: A Harmonized Survival Benchmark Across Dynamic and Early-Window Representations MedFormer-UR: Uncertainty-Routed Transformer for Medical Image Classification Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs SenBen: Sensitive Scene Graphs for Explainable Content Moderation eBandit: Kernel-Driven Reinforcement Learning for Adaptive Video Streaming Accelerating Transformer-Based Monocular SLAM via Geometric Utility Scoring Deep Learning-Based Tracking and Lineage Reconstruction of Ligament Breakup Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding On Semiotic-Grounded Interpretive Evaluation of Generative Art Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation QARIMA: A Quantum Approach To Classical Time Series Analysis StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement Learning From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity Detection of Hate and Threat in Digital Forensics: A Case-Driven Multimodal Approach Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines Joint Interference Detection and Identification via Adversarial Multi-task Learning Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs Act or Escalate? Evaluating Escalation Behavior in Automation with Language Models Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers Multivariate Time Series Anomaly Detection via Dual-Branch Reconstruction and Autoregressive Flow-based Residual Density Estimation On the Spectral Geometry of Cross-Modal Representations: A Functional Map Diagnostic for Multimodal Alignment Structured Exploration and Exploitation of Label Functions for Automated Data Annotation MolPaQ: Modular Quantum-Classical Patch Learning for Interpretable Molecular Generation QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation Generating High Quality Synthetic Data for Dutch Medical Conversations Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models Reinforcement-aware Knowledge Distillation for LLM Reasoning SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework A Horizon-Aware Decision-Support Framework for Demand Forecasting Model Selection in Resilient Production Planning H-AdminSim: A Multi-Agent Simulator for Realistic Hospital Administrative Workflows with FHIR Integration AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts Reasoning Models Will Sometimes Lie About Their Reasoning Multi-agent Adaptive Mechanism Design Relational Visual Similarity From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting HCAST: Human-Calibrated Autonomy Software Tasks OmniPrism: Learning Disentangled Visual Concept for Image Generation
A Note on Hybrid Online Reinforcement and Imitation Learning for LLMs: Formulations and Algorithms
Yingru Li, Ziniu Li, Jiacai Liu · 2025-12-29 · via cs.AI updates on arXiv.org

We present a unified framework for Large Language Model (LLM) fine-tuning that integrates Imitation Learning and Reinforcement Learning. By analyzing the gradient of a composite objective combining trajectory-level KL divergence with task rewards, we derive a natural decomposition into two components: (1) an analytically computable Dense Gradient for token-level imitation, and (2) a Monte Carlo estimated Sparse Gradient for long-horizon reward optimization. The Dense Gradient admits a closed-form logit-level formula, enabling efficient GPU implementation.

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。