StateComp: Learning When to Compress History in Long Horizon Agents
cs.AI
Submitted: 2026-09-23
Updated: 2026-09-23
Terminology
Sources
- ReAct: Synergizing Reasoning and Acting in Language Models
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction
- In-context Autoencoder for Context Compression in a Large Language Model
- Self-Compacting Language Model Agents
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- Self-GC: Self-Governing Context for Long-Horizon LLM Agents
- CoMem: Context Management with A Decoupled Long-Context Model
- SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
- MemGPT: Towards LLMs as Operating Systems
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
- ACM: Agentic Context Management for Long Horizon Tasks
- InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- GLM-5: from Vibe Coding to Agentic Engineering
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection