# SkillEffect: Checked Lowering for Memory-Bounded Agent Tools

arXiv: https://arxiv.org/abs/2608.17007 · HTML: https://mlsanity.com/paper/2608.17007/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

## Builds on (most cited first, 22 of 22)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Agent Contracts: A Formal Framework for Resource-Bounded Autonomous AI Systems](https://mlsanity.com/paper/2601.08815/) (2026)
- [SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses](https://mlsanity.com/paper/2604.03088/) (2026)
- [CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning](https://mlsanity.com/paper/2411.16313/) (2024)
- [AgentCgroup: Understanding and Controlling OS Resources of AI Agents](https://mlsanity.com/paper/2602.09345/) (2026)
- [Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents](https://mlsanity.com/paper/2606.03895/) (2026)
- [SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents](https://mlsanity.com/paper/2605.03353/) (2026)
- [Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents](https://mlsanity.com/paper/2606.22504/) (2026)
- [SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces](https://mlsanity.com/paper/2605.15215/) (2026)
- [TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows](https://mlsanity.com/paper/2608.02680/) (2026)
- [PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization](https://mlsanity.com/paper/2607.19653/) (2026)
- [Control Under Compression: Reliability Frontiers for Tool-Using Agents](https://mlsanity.com/paper/2608.01056/) (2026)
- [Resource-Guided Program Synthesis](https://mlsanity.com/paper/1904.07415/) (2019)
- [Dias: Dynamic Rewriting of Pandas Code](https://mlsanity.com/paper/2303.16146/) (2023)
- [Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents](https://mlsanity.com/paper/2604.04131/) (2026)
- [Evaluating LLMs on Real-World Software Performance Optimization](https://mlsanity.com/paper/2606.25530/) (2026)
- [Verifying and Synthesizing Constant-Resource Implementations with Types](https://mlsanity.com/paper/1801.01896/) (2018)
- [RuleFlow : Generating Reusable Program Optimizations with LLMs](https://mlsanity.com/paper/2602.09051/) (2026)
- [An Extensible and Verifiable Language for Query Rewrite Rules](https://mlsanity.com/paper/2605.05536/) (2026)
- [MOA: A Profiling-Guided LLM Framework for Memory-Optimization Automation at Codebase Scale](https://mlsanity.com/paper/2606.31368/) (2026)
- [Auto: The AGI Compiler](https://mlsanity.com/paper/2607.04542/) (2026)
- [SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries](https://mlsanity.com/paper/2608.05604/) (2026)

## Abstract (arXiv)

Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs. However, when models turn this guidance into code for existing tool interfaces, even a semantically correct program may load an entire input and exceed the memory available to one tool call. We present SkillEffect, a checked-lowering runtime for computations with a recoverable source relation, an audited bounded implementation, and a registered output postcondition. Before granting execution authority, an independent checker rebuilds each proposed lowering from the submitted program and immutable input. Every relation plugin supplies a source recognizer, input-fact extractor, bounded-IR constructor, arena-bound function, and postcondition; one common runtime provides checked selection, bounded-VM execution, atomic capacity leasing, and staged publication. Generality in SkillEffect is architectural rather than automatic: each supported computation requires an audited relation plugin, while the dispatch, resource-control, execution, and publication mechanisms are shared across plugins. Across six operator families, bounded access substantially reduces peak memory and improves completion under externally fixed caps. Six plugins instantiate the same contract across five execution patterns, from streaming reduction to bounded-heap Top-k. The XLSX onboarding study and Top-k extension show that a new relation and a new retained-state pattern reuse the same trust boundary, while the checker accepts all evaluated legal configurations and rejects all adversarial proposals. Together, these results show that one checked-lowering architecture can enforce heterogeneous registered memory relations at Agent tool dispatch.