RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent
cs.AI, cs.LG, cs.MA
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Training-Free Group Relative Policy Optimization
- Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
- Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecture
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- Humanity's Last Exam
- Experience-Guided Adaptation of Inference-Time Reasoning Strategies
- Reinforcement Learning for Self-Improving Agent with Skill Library
- BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
- EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
- General Agentic Memory Via Deep Research
- Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
- Scaling Test-time Compute for LLM Agents
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
- Agents' Last Exam
- 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