Agentic Context Management for Multi-Turn Human-AI Conversations
cs.AI, cs.CL
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/openclaw/openclaw
Terminology
Sources
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Memp: Exploring Agent Procedural Memory
- ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
- Do LLMs Benefit From Their Own Words?
- ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models
- LLMs Get Lost In Multi-Turn Conversation
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- MemoBrain: Executive Memory as an Agentic Brain for Reasoning
- THREAD: Thinking Deeper with Recursive Spawning
- Self-Distillation Enables Continual Learning
- MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation
- U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents
- Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- System 2 Attention (is something you might need too)
- EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
- CollabLLM: From Passive Responders to Active Collaborators
- Learning to Continually Learn via Meta-learning Agentic Memory Designs
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