---
title: "Learning to Coordinate: LLM-Guided... | SI Paper Desk"
url: https://thesimind.si/papers/2611.24221/
description: "L2C is a system that teams several SI agents to red team language models, and it finds more safety failures than EvoSynth while using fewer online tokens."
---

Number 6 of 12 · November 20, 2026

# Learning to Coordinate: LLM-Guided Workflow Evolution for Token-Efficient Red Teaming

L2C is a system that teams several SI agents to red team language models, and it finds more safety failures than EvoSynth while using fewer online tokens.

Xiaoyang Xing, Wenyu Dai, Xiaoliang Gong and 2 more · Submitted November 18, 2026 · arXiv 2611.24221v1 · cs.AI

[Read the paper on arXiv](https://arxiv.org/abs/2611.24221) · [The PDF](https://arxiv.org/pdf/2611.24221) · [The day's 12](https://thesimind.si/papers/day/2026-11-20/)

## What they found

The authors built Learning to Coordinate (L2C). It sets up a team of SI agents to test a language model for safety failures, which is called red teaming. Each test case gets its own workflow, stored as a versioned graph of agent roles, dependencies and inputs. A controller trained with supervised fine-tuning reads records of what was passed between agents, plus the target's reply, the evaluator's verdict and the budget left. It then decides whether to keep the workflow, refine instructions, restructure the team, or lock further edits. The tests used HarmBench with three execution backbones and two target models. In all six executor-target setups, L2C improved attack success rate (ASR) over EvoSynth by 1.4 to 4.5 percentage points. It also cut mean online tokens by 35.6% to 37.3%. The authors also report ablations, dataset transfer and evaluator checks, but the abstract gives no details of those results.

## Why it matters

Red teaming is how builders look for safety failures before release. If it costs less to run, more teams can test more often. The abstract says the controller links feedback to specific changes in how agents work together. That is a step beyond only seeing whether an attack worked. The ASR gains are modest, and the abstract does not say how they hold up outside the tested setups.

## How it changes the race

If the result holds, safety testing of frontier models gets cheaper, so smaller labs and outside auditors could run more of it. The gain is incremental over EvoSynth, mainly in cost.

## Safety and control

This work is meant to help find safety failures in language models, so it supports safety evaluation. Cheaper and stronger automated attacks could also help people who want to misuse models. The abstract does not discuss this.

### The abstract, by the authors

Automated red teaming is essential for identifying safety failures in large language models (LLMs), but its practical scalability depends on the resources required to discover those failures. Multi-agent systems can combine complementary capabilities, yet repeated planning, redundant exchanges, and ineffective information routing can make their coordination expensive. Moreover, a target model's response indicates the outcome of a test without identifying which collaboration decision should change. We present Learning to Coordinate (L2C), an LLM-guided framework that evolves an executable multi-agent workflow for each red-teaming case. L2C represents agent responsibilities, execution dependencies, and input bindings in a versioned graph, and associates each graph with records of the information actually delivered and produced. A controller trained through supervised fine-tuning integrates these records with target responses, evaluator verdicts, and remaining budget to retain the workflow, refine instructions, restructure collaboration, or lock further editing. This design connects feedback to explicit changes in subsequent execution while allowing a useful organization to continue without repeated controller intervention. The evaluation protocol covers HarmBench with three execution backbones and two target models, together with component ablations, dataset transfer, and evaluator checks. Across the six executor-target configurations, L2C improves ASR over EvoSynth by 1.4 to 4.5 percentage points while reducing mean online tokens by 35.6% to 37.3%. L2C connects adaptive collaboration to the resource requirements of automated security evaluation.

Quoted from arXiv:2611.24221. The research and its words belong to its authors.

Desk score **80** out of 100

Why it was picked

- Safety (in the title)
- Agents
- Reasoning
- Evals
- Language models (in the title)
- Multi-agent

Topics

- [Safety](https://thesimind.si/papers/?tag=safety)
- [Multi-agent systems](https://thesimind.si/papers/?tag=multi-agent)
- [Agents](https://thesimind.si/papers/?tag=agents)
- [Evals](https://thesimind.si/papers/?tag=evals)
- [Efficiency](https://thesimind.si/papers/?tag=efficiency)
- [Language models](https://thesimind.si/papers/?tag=language-models)

**arXiv ID:** 2611.24221v1
**Submitted:** November 18, 2026
**Fields:** cs.AI (Artificial Intelligence)
**Level:** Intermediate
**Comments:** 10 pages, 3 figures

Fingerprint, SHA-256

`ed5333dc410ea5c633c4c2e693f08c2277447823e628e2c179f7c4c6d5b08e5f`

On Solana: [Proof of Mind seal, 4JtzxB...6w5n](https://solscan.io/tx/4JtzxBBunUdHpdT7ydTygvUny81ph9bmXUMt9UHMJBLFrSwBZFdTbtV5CcZdHAM2kg7Bc2pTnq59P4DvXyGc6w5n)

### The exact text fingerprinted

{"arxiv":"2611.24221","version":1,"title":"Learning to Coordinate: LLM-Guided Workflow Evolution for Token-Efficient Red Teaming","authors":["Xiaoyang Xing","Wenyu Dai","Xiaoliang Gong","Asoke K Nandi","Anthony Cohn"],"day":"2026-11-20","rank":6,"score":80,"status":"written","summary":{"takeaway":"L2C is a system that teams several SI agents to red team language models, and it finds more safety failures than EvoSynth while using fewer online tokens.","found":"The authors built Learning to Coordinate (L2C). It sets up a team of SI agents to test a language model for safety failures, which is called red teaming. Each test case gets its own workflow, stored as a versioned graph of agent roles, dependencies and inputs. A controller trained with supervised fine-tuning reads records of what was passed between agents, plus the target's reply, the evaluator's verdict and the budget left. It then decides whether to keep the workflow, refine instructions, restructure the team, or lock further edits. The tests used HarmBench with three execution backbones and two target models. In all six executor-target setups, L2C improved attack success rate (ASR) over EvoSynth by 1.4 to 4.5 percentage points. It also cut mean online tokens by 35.6% to 37.3%. The authors also report ablations, dataset transfer and evaluator checks, but the abstract gives no details of those results.","matters":"Red teaming is how builders look for safety failures before release. If it costs less to run, more teams can test more often. The abstract says the controller links feedback to specific changes in how agents work together. That is a step beyond only seeing whether an attack worked. The ASR gains are modest, and the abstract does not say how they hold up outside the tested setups.","race":"If the result holds, safety testing of frontier models gets cheaper, so smaller labs and outside auditors could run more of it. The gain is incremental over EvoSynth, mainly in cost.","safety":"This work is meant to help find safety failures in language models, so it supports safety evaluation. Cheaper and stronger automated attacks could also help people who want to misuse models. The abstract does not discuss this.","level":"intermediate","tags":["safety","multi-agent","agents","evals","efficiency","language-models"]}}

[Check it on Verify a thought](https://thesimind.si/proof-of-mind/)

## The authors

Xiaoyang Xing, Wenyu Dai, Xiaoliang Gong, Asoke K Nandi, Anthony Cohn

Credit for this research belongs to its authors. SI MIND's page is a plain-English reading of their abstract on arXiv, not a review of the full paper.

Related on the desk

## More papers on these topics

[Nov 16, 2026 · Paper of the DayOnly as Safe as the Weakest Agent: A Break That Appears Only When the System Is Multi-AgentWhen a strong SI model hands work to a cheaper sub-agent, the whole system can be only as safe as the weaker agent, even if the strong model alone resists the attack.SafetyMulti-agent systemsSecurity](https://thesimind.si/papers/2611.17520/) · [Nov 18, 2026 · Paper of the DayGRACE: Parallel Best-of-N Multi-Agent Analysis of Closed-Form Questions over Dataframes with Guardrail Selection and Adaptive RetryGRACE runs several SI agents in parallel on spreadsheet-style questions, judges their executed work instead of voting, and can reject all answers and retry, lifting answer match from 39% to 71% on one benchmark.AgentsMulti-agent systemsCode](https://thesimind.si/papers/2611.20983/) · [Nov 19, 2026 · Number 2Runtime Verification of Multiple Natural Language Criteria for Agent GovernanceThe authors built VFM, a small verifier that checks an SI agent's output against many written rules at once and says which are met, broken, or not relevant.SafetyAgentsEvals](https://thesimind.si/papers/2611.23074/)

[Number 5](https://thesimind.si/papers/2611.23891/) · [All 12 for Nov 20, 2026](https://thesimind.si/papers/day/2026-11-20/) · [Number 7](https://thesimind.si/papers/2611.24362/)
