SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation

arXiv:2609.32391 · cs.AI, cs.DC, cs.LG · Submitted 2026-09-26 · Read on arXiv

cs.AI, cs.DC, cs.LG

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/garrytan/gbrain

Terminology

• Benchmark — 102× in this paper · explained in 2 episodes
• Accuracy — 20× in this paper · explained in 1 episode
• Adaptability — 10× in this paper · explained in 1 episode
• Trace — 10× in this paper · explained in 2 episodes
• Abstraction — 7× in this paper · explained in 1 episode
• Benchmarking — 7× in this paper · explained in 3 episodes
• GRPO — 7× in this paper · explained in 6 episodes
• Core — 5× in this paper · explained in 2 episodes
• Distillation — 5× in this paper · explained in 2 episodes
• On-Policy Distillation — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Continual Learning — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Agent Harness — 2× in this paper · explained in 2 episodes
• Agentic Evaluation — 2× in this paper · explained in 1 episode
• Decoupling — 2× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 2× in this paper
• AI Agents — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Agent Memory — 1× in this paper · explained in 1 episode
• Generative AI — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
• AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
• Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
• Meta-Harness: End-to-End Optimization of Model Harnesses
• HorizonBench: Long-Horizon Personalization with Evolving Preferences
• Evaluating Very Long-Term Conversational Memory of LLM Agents
• Training Software Engineering Agents and Verifiers with SWE-Gym
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents
• Self-Distillation Enables Continual Learning
• Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
• Learning to (Learn at Test Time): RNNs with Expressive Hidden States
• AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
• Voyager: An Open-Ended Embodied Agent with Large Language Models

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