mlsanityData to 14 Oct 2026

FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows

arXiv 2608.01772 ↗First posted 3 Aug 2026cs.AIcited by 0

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

LLM agents increasingly run policy-bound enterprise workflows, where they must apply rules consistently and stay auditable. Deploying such an agent is the start of its long-term maintenance cycle: it must adapt to a stream of operational signals, yet reliably turning these sparse, unlabeled signals into reusable skill revisions is hard, and a careless update can trade one task category's accuracy for the overall gain, revive a resolved failure, or land at an undeployable cost. We present ESCROW, a post-deployment maintenance framework that updates an agent's external, reviewable skills under a Strict Update Boundary: the LLM proposes candidate revisions, but only an empirically evaluated version is deployed. It combines distributed diagnosis with consensus, a per-category non-regression guard, cross-cycle anti-regression, and accuracy--cost Pareto search, emitting a versioned, auditable diff per change. In real production on our internal financial document-auditing system, it attains the strongest evaluated accuracy--cost trade-off among baselines, with a transfer probe on public τ-bench.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 23 of its 32 references that are in the map. First posted on arXiv 3 Aug 2026.

Builds on

23 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Towards Enforcing Company Policy Adherence in Agentic Workflows22 Jul

Other references · 22

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  5. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  6. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  7. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  8. 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Taskscited by 315
  9. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 278
  10. 2026Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skillscited by 187
  11. 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 115
  12. 2026Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forwardcited by 113
10 more
  1. 2026EvoSkill: Automated Skill Discovery for Multi-Agent Systemscited by 107
  2. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 100
  3. 2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalizationcited by 94
  4. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 76
  5. 2026Memento-Skills: Let Agents Design Agentscited by 62
  6. 2026MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wildcited by 37
  7. 2025Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidancecited by 14
  8. 2026GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agentscited by 11
  9. 2025Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Supportcited by 10
  10. 2026ASDA: Automated Skill Distillation and Adaptation for Financial Reasoningcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate
  2. 2026It Takes Workflows to Evolve Better Workflows
  3. 2026On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
  4. 2026Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems
  5. 2026Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds
  6. 2026Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents
  7. 2026FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
  8. 2026Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows