mlsanityData to 14 Oct 2026

RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents

arXiv 2606.20638 ↗First posted 2 Jun 2026cs.AI cs.LGcited by 1

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Large language models are increasingly deployed as long-lived agents that must adapt across users, tasks, domains, modalities, and feedback regimes without access to model weights. Existing black-box adaptation methods typically optimize a single prompt, maintain an undifferentiated memory, or rely on repeated rollout-heavy search. However, these designs struggle when streams of input are nonstationary, feedback is sparse, and failures from one task family can contaminate behavior on another. We introduce RIZZ (Routing Interactions to Near Zero-interference Zones), a continual adaptation framework for compound language-model systems that learns entirely through verifier-gated memory, routing, and prompt compilation. RIZZ organizes input streams into dynamically spawned memory branches. At inference time, either while online or offline, a context-aware router selects or creates a branch that retrieves branch-local, global, graph-structured, and working-memory context, which is compiled into a bounded prompt together with retrieved task evidence. After the model acts, task verifiers score the output, and only verified interactions can update memory, promote reusable rules, demote harmful rules, or create anti-patterns. This yields a black-box agent that improves through persistent natural-language feedback while explicitly controlling interference. RIZZ targets the regime where adaptation must occur online under context budgets. Finally, we demonstrate the effectiveness of our framework against state-of-the-art baselines on competitive benchmarks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 31 of its 41 references that are in the map. First posted on arXiv 2 Jun 2026.

Builds on

31 of 41 references.

References · 31

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  7. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  8. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  9. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  10. 2021Learning to Prompt for Continual Learningcited by 944
  11. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  12. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 722
19 more
  1. 2025GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningcited by 542
  2. 2024Understanding the planning of LLM agents: A surveycited by 421
  3. 2026Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Rankingcited by 230
  4. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 163
  5. 2023TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Modelscited by 66
  6. 2024StreamBench: Towards Benchmarking Continuous Improvement of Language Agentscited by 47
  7. 2025Feedback Descent: Open-Ended Text Optimization via Pairwise Comparisoncited by 44
  8. 2023Maintaining Plasticity in Deep Continual Learningcited by 43
  9. 2024Rethinking Data Selection for Supervised Fine-Tuningcited by 35
  10. 2024ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedbackcited by 13
  11. 2022Continual task learning in natural and artificial agentscited by 12
  12. 2023Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptationcited by 12
  13. 2026QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understandingcited by 11
  14. 2024Continual Learning Using Only Large Language Model Promptingcited by 5
  15. 2025MetaSym: A Symplectic Meta-learning Framework for Physical Intelligencecited by 5
  16. 2025Meta-learning characteristics and dynamics of quantum systemscited by 4
  17. 2026On the Plasticity and Stability for Post-Training Large Language Modelscited by 4
  18. 2026ELLA: Efficient Lifelong Learning for Adapters in Large Language Modelscited by 3
  19. 2026Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columnscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Knowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition
  2. 2025Routing-Based Continual Learning for Multimodal Large Language Models
  3. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
  4. 2026Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents
  5. 2026Recurrent Harness for Agentic Continual Learning
  6. 2026LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models
  7. 2026AdaMEM: Test-Time Adaptive Memory for Language Agents
  8. 2026Choosing How to Remember: Adaptive Memory Structures for LLM Agents