# Herding CATs: ALARA for Agent Harness Engineering in Portable Composable Multi-Agent Teams

arXiv: https://arxiv.org/abs/2603.20380 · HTML: https://mlsanity.com/paper/2603.20380/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 57 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 30 of 34)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [Lessons from the Trenches on Reproducible Evaluation of Language Models](https://mlsanity.com/paper/2405.14782/) (2024)
- [Evaluation and Benchmarking of LLM Agents: A Survey](https://mlsanity.com/paper/2507.21504/) (2025)
- [TaskBench: Benchmarking Large Language Models for Task Automation](https://mlsanity.com/paper/2311.18760/) (2023)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Machine Learning Operations (MLOps): Overview, Definition, and Architecture](https://mlsanity.com/paper/2205.02302/) (2022)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [Small LLMs Are Weak Tool Learners: A Multi-LLM Agent](https://mlsanity.com/paper/2401.07324/) (2024)
- [Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents](https://mlsanity.com/paper/2503.15547/) (2025)
- [Design Patterns for Securing LLM Agents against Prompt Injections](https://mlsanity.com/paper/2506.08837/) (2025)
- [Levels of Autonomy for AI Agents](https://mlsanity.com/paper/2506.12469/) (2025)
- [When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail](https://mlsanity.com/paper/2601.04748/) (2026)
- [Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature](https://mlsanity.com/paper/2507.06000/) (2025)
- [Everything is Context: Agentic File System Abstraction for Context Engineering](https://mlsanity.com/paper/2512.05470/) (2025)
- [A quantum semantic framework for natural language processing](https://mlsanity.com/paper/2506.10077/) (2025)

## Built on by (most cited first, 2 of 2)

- [Minimal Oversight: Uncertainty-Aware Governance for Delegated AI Systems](https://mlsanity.com/paper/2606.15563/) (2026)
- [SHarP: Saliency-based Pruning of Agent Harnesses](https://mlsanity.com/paper/2610.04178/) (2026)

## Abstract (arXiv)

Industry practitioners and academic researchers regularly use multi-agent systems to accelerate their work, but the applications through which users operate these systems do not provide a simple, unified mechanism for scalably managing critical components of the agent harness. This lack of control adversely impacts both the quality of individual human-agent interactions and reduces the capacity for practitioners to coordinate context engineering efforts. The behavioral specifications that define what agents in such systems can do remain fragmented across prose instruction files -- for which compliance cannot be guaranteed -- or framework-internal configurations, making these specifications difficult to share, version, or collaboratively maintain across teams and projects. Applying the ALARA principle from radiation safety (exposures kept as low as reasonably achievable) to context, we introduce a context-agent-tool (CAT) data layer expressed through interrelated plain-text files, allowing users to directly declare tool access for each agent and to modify the tools themselves that are used by the agents when processing. We demonstrate capability of this CAT data layer to enable real agentic usage by using a command-line shell that loads the team and executes agent runs -- textttnpcsh -- and evaluating 22 locally-hosted models from 0.6B to 35B parameters across 115 practical tasks spanning file operations, web search, multi-step scripting, tool chaining, and multi-agent delegation. We characterize which model families succeed in certain task categories and where they break down across ~2500 total executions.