Cover Image

TVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kumar, Abhishek Vijaya, Kataria, Bhaskar, Oh, Byungsoo, Manzoor, Emaad, Singh, Rachee
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CCL-Bench 1.0: A Trace-Based Benchmark for LLM Infrastructure
by: Ding, Eric, et al.
Published: (2026)

FlashMoE: Fast Distributed MoE in a Single Kernel
by: Aimuyo, Osayamen Jonathan, et al.
Published: (2025)

Eliminating Hidden Serialization in Multi-Node Megakernel Communication
by: Oh, Byungsoo, et al.
Published: (2026)

LUMION: Fast Fault Recovery for ML Jobs Using Programmable Optical Fabrics
by: Kumar, Abhishek Vijaya, et al.
Published: (2025)

Efficient AllReduce with Stragglers
by: Devraj, Arjun, et al.
Published: (2025)

Morphlux: Transforming Torus Fabrics for Efficient Multi-tenant ML
by: Kumar, Abhishek Vijaya, et al.
Published: (2025)

Learning When to Quit in Sales Conversations
by: Manzoor, Emaad, et al.
Published: (2025)

AQUA: Network-Accelerated Memory Offloading for LLMs in Scale-Up GPU Domains
by: Kumar, Abhishek Vijaya, et al.
Published: (2024)

PCCL: Photonic circuit-switched collective communication for distributed ML
by: Kumar, Abhishek Vijaya, et al.
Published: (2025)

Photonic Rails in ML Datacenters with Opus
by: Ding, Eric, et al.
Published: (2026)

Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning
by: Hu, Diyi, et al.
Published: (2026)

PostTrainBench: Can LLM Agents Automate LLM Post-Training?
by: Rank, Ben, et al.
Published: (2026)

Value Drifts: Tracing Value Alignment During LLM Post-Training
by: Bhatia, Mehar, et al.
Published: (2025)

Chip-to-chip photonic connectivity in multi-accelerator servers for ML
by: Kumar, Abhishek Vijaya, et al.
Published: (2025)

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
by: Zhu, Dingwei, et al.
Published: (2025)

LLM Agents for Bargaining with Utility-based Feedback
by: Oh, Jihwan
Published: (2025)

Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
by: Hu, Pingbang, et al.
Published: (2026)

10Cache: Heterogeneous Resource-Aware Tensor Caching and Migration for LLM Training
by: Afroz, Sabiha, et al.
Published: (2025)

RDAR: Reward-Driven Agent Relevance Estimation for Autonomous Driving
by: Bosio, Carlo, et al.
Published: (2025)

Digi-Q: Learning Q-Value Functions for Training Device-Control Agents
by: Bai, Hao, et al.
Published: (2025)

RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use
by: Chai, Jiajun, et al.
Published: (2025)

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents
by: Jeon, Hyesung, et al.
Published: (2026)

DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
by: Zhu, Dingwei, et al.
Published: (2026)

Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States
by: Yuan, Yurun, et al.
Published: (2026)

GraphFLEx: Structure Learning Framework for Large Expanding Graphs
by: Kataria, Mohit, et al.
Published: (2025)

CacheFormer: High Attention-Based Segment Caching
by: Singh, Sushant, et al.
Published: (2025)

Training Transformers for KV Cache Compressibility
by: Gelberg, Yoav, et al.
Published: (2026)

SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference
by: Smith, Jeff
Published: (2025)

Unlocking the Address Book: Dissecting the Sparse Semantic Structure of LLM Key-Value Caches via Sparse Autoencoders
by: Ma, Qingsen, et al.
Published: (2025)

How Many Tools Should an LLM Agent See? A Chance-Corrected Answer
by: Repantis, Vyzantinos, et al.
Published: (2026)

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
by: Thede, Lukas, et al.
Published: (2026)

Consolidating Rewarded Perturbations for LLM Post-Training
by: Zhang, Zheyu, et al.
Published: (2026)

Automatic Configuration of LLM Post-Training Pipelines
by: Chwa, Channe, et al.
Published: (2026)

How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment
by: Zhu, Rui, et al.
Published: (2026)

Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents
by: Chu, Kexin, et al.
Published: (2026)

Memory-Induced Tool-Drift in LLM Agents
by: Dabas, Mahavir, et al.
Published: (2026)

Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data
by: Acikgoz, Emre Can, et al.
Published: (2026)

GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching
by: Regmi, Sajal, et al.
Published: (2024)

Learning to Evict from Key-Value Cache
by: Moschella, Luca, et al.
Published: (2026)

LLM Agents Making Agent Tools
by: Wölflein, Georg, et al.
Published: (2025)