mlsanityData to 7 Oct 2026

Agentic Router: An Execution-Grounded Continual Learning Approach With Memory

arXiv 2608.09184 ↗First posted 10 Aug 2026cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large language model (LLM) agents provide a promising interface for command-line-based network operations, but a plausible command may still fail or introduce operational risk after execution. Existing approaches mainly focus on command generation or final configuration correctness, and do not use execution-grounded experience to jointly improve candidate coverage and action selection. We propose an execution-grounded dual-path consequence-aware agent for CLI-based SONiC operations, which generates multiple complete actions, predicts their execution consequences, and selects the final action through utility- and risk-aware reranking. The proposal-side path abstracts reusable operational lessons into retrievable guidance to improve feasible-action coverage without modifying the proposal LLM, while the selection-side path adapts the consequence predictor through session-level LoRA updates using real SSH feedback to improve conditional selection quality. Experiments over multi-turn SONiC operation sessions with different Qwen3 proposal models show that the framework improves feasible-action coverage and top-1 execution success, and that the two adaptation paths provide complementary gains over interaction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 10 of its 17 references that are in the map. First posted on arXiv 10 Aug 2026.

Builds on

10 of 17 references.

References · 10

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  8. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  9. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  10. 2024Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learningcited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning CLI Agents with Structured Action Credit under Selective Observation
  2. 2026KAIJU: An Executive Kernel for Intent-Gated Execution of LLM Agents
  3. 2026Callability Is Not Operability: Controlled Interface Interventions for LLM Agents
  4. 2026AgentAbstain: Do LLM Agents Know When Not to Act?
  5. 2026Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents
  6. 2026Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems
  7. 2026NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration
  8. 2026AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving