Image de couverture de livre

Absorber LLM: Harnessing Causal Synchronization for Test-Time Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Zhixin, Zhang, Shabo, Wu, Chengcan, Wei, Zeming, Sun, Meng
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Computation and Language Software Engineering Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing
par: Wei, Zeming, et autres
Publié: (2026)

Secure LLM Fine-Tuning via Safety-Aware Probing
par: Wu, Chengcan, et autres
Publié: (2025)

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction
par: Wei, Zeming, et autres
Publié: (2025)

Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
par: Wu, Chengcan, et autres
Publié: (2025)

Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
par: Zhang, Zhixin, et autres
Publié: (2025)

ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
par: Lian, Junbo Jacob, et autres
Publié: (2026)

MILE: A Mutation Testing Framework of In-Context Learning Systems
par: Wei, Zeming, et autres
Publié: (2024)

ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
par: Zhang, Yihao, et autres
Publié: (2026)

Automata-Based Steering of Large Language Models for Diverse Structured Generation
par: Luan, Xiaokun, et autres
Publié: (2025)

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
par: Zhang, Yihao, et autres
Publié: (2024)

LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation
par: Ma, Zeyuan, et autres
Publié: (2024)

AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI
par: Rana, Manik, et autres
Publié: (2025)

Boosting Jailbreak Attack with Momentum
par: Zhang, Yihao, et autres
Publié: (2024)

Causal LLM Routing: End-to-End Regret Minimization from Observational Data
par: Tsiourvas, Asterios, et autres
Publié: (2025)

Scaling Test-Time Compute for Agentic Coding
par: Kim, Joongwon, et autres
Publié: (2026)

Toward Training Superintelligent Software Agents through Self-Play SWE-RL
par: Wei, Yuxiang, et autres
Publié: (2025)

RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
par: Wei, Zeming, et autres
Publié: (2026)

OptiLoop: Coordination-in-the-Loop Verification and Repair for LLM-Generated Optimization Agents
par: Xu, Yujia, et autres
Publié: (2026)

Does Few-Shot Learning Help LLM Performance in Code Synthesis?
par: Xu, Derek, et autres
Publié: (2024)

Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering
par: Zeng, Guangtao, et autres
Publié: (2025)

Let the Code LLM Edit Itself When You Edit the Code
par: He, Zhenyu, et autres
Publié: (2024)

Inverse Optimality for Fair Digital Twins: A Preference-based approach
par: Masti, Daniele, et autres
Publié: (2025)

Exploring the Robustness of In-Context Learning with Noisy Labels
par: Cheng, Chen, et autres
Publié: (2024)

CorrectHDL: Agentic HDL Design with LLMs Leveraging High-Level Synthesis as Reference
par: Xu, Kangwei, et autres
Publié: (2025)

Agentless: Demystifying LLM-based Software Engineering Agents
par: Xia, Chunqiu Steven, et autres
Publié: (2024)

LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models
par: Feng, Xiaoning, et autres
Publié: (2022)

SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning
par: Chi, Yizhou, et autres
Publié: (2024)

ToolFactory: Automating Tool Generation by Leveraging LLM to Understand REST API Documentations
par: Ni, Xinyi, et autres
Publié: (2025)

A Survey on Code Generation with LLM-based Agents
par: Dong, Yihong, et autres
Publié: (2025)

Enabling Performant and Flexible Model-Internal Observability for LLM Inference
par: Yu, Nengneng, et autres
Publié: (2026)

Verification Limits Code LLM Training
par: Gureja, Srishti, et autres
Publié: (2025)

Adaptable and Precise: Enterprise-Scenario LLM Function-Calling Capability Training Pipeline
par: Zeng, Guancheng, et autres
Publié: (2024)

WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
par: Fan, Shengda, et autres
Publié: (2024)

Non-Determinism of "Deterministic" LLM Settings
par: Atil, Berk, et autres
Publié: (2024)

What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
par: Bensalem, Saddek, et autres
Publié: (2023)

OBsmith: LLM-Powered JavaScript Obfuscator Testing
par: Jiang, Shan, et autres
Publié: (2025)

Deployability-Centric Infrastructure-as-Code Generation: Fail, Learn, Refine, and Succeed through LLM-Empowered DevOps Simulation
par: Zhang, Tianyi, et autres
Publié: (2025)

$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
par: Zhang, Dylan, et autres
Publié: (2024)

Issue Localization via LLM-Driven Iterative Code Graph Searching
par: Jiang, Zhonghao, et autres
Publié: (2025)

Planning to Explore: Curiosity-Driven Planning for LLM Test Generation
par: Amayuelas, Alfonso, et autres
Publié: (2026)