From History to State: Constant-Context Skill Learning for LLM Agents
cs.AI
Submitted: 2026-05-06
Updated: 2026-11-06
Comments: Accepted to NeurIPS 2026. Code: https://github.com/haoyangxie/constant-context-skill-learning
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LightMem: Lightweight and Efficient Memory-Augmented Generation
- Group-in-Group Policy Optimization for LLM Agent Training
- AgentRefine: Enhancing Agent Generalization through Refinement Tuning
- Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
- Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
- Odyssey: Empowering Minecraft Agents with Open-World Skills
- Agentic Critical Training
- Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- REMem: Reasoning with Episodic Memory in Language Agent
- Qwen3.5-Omni Technical Report
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- A-MEM: Agentic Memory for LLM Agents
- MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
- Agent Learning via Early Experience
- ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents