# Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control

arXiv: https://arxiv.org/abs/2601.20090 · HTML: https://mlsanity.com/paper/2601.20090/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 23 of 23)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [The frontier of simulation-based inference](https://mlsanity.com/paper/1911.01429/) (2019)
- [Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows](https://mlsanity.com/paper/1805.07226/) (2018)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [Automatic Posterior Transformation for Likelihood-Free Inference](https://mlsanity.com/paper/1905.07488/) (2019)
- [Conformal Language Modeling](https://mlsanity.com/paper/2306.10193/) (2023)
- [Benchmarking Simulation-Based Inference](https://mlsanity.com/paper/2101.04653/) (2021)
- [Conformal Inference of Counterfactuals and Individual Treatment Effects](https://mlsanity.com/paper/2006.06138/) (2020)
- [Forking Uncertainties: Reliable Prediction and Model Predictive Control with Sequence Models via Conformal Risk Control](https://mlsanity.com/paper/2310.10299/) (2023)
- [A Bayesian Framework for Digital Twin-Based Control, Monitoring, and Data Collection in Wireless Systems](https://mlsanity.com/paper/2212.01351/) (2022)
- [AgentRAN: An Agentic AI Architecture for Autonomous Control of Open 6G Networks](https://mlsanity.com/paper/2508.17778/) (2025)
- [Counterfactual Token Generation in Large Language Models](https://mlsanity.com/paper/2409.17027/) (2024)
- [Gumbel Counterfactual Generation From Language Models](https://mlsanity.com/paper/2411.07180/) (2024)
- [BostonTwin: the Boston Digital Twin for Ray-Tracing in 6G Networks](https://mlsanity.com/paper/2403.12289/) (2024)
- [What If We Had Used a Different App? Reliable Counterfactual KPI Analysis in Wireless Systems](https://mlsanity.com/paper/2410.00150/) (2024)
- [Reflection-Driven Self-Optimization 6G Agentic AI RAN via Simulation-in-the-Loop Workflows](https://mlsanity.com/paper/2512.20640/) (2025)

## Built on by (most cited first, 1 of 1)

- [Advanced AI Service Provisioning in O-RAN through LLM Engine Integration](https://mlsanity.com/paper/2605.23809/) (2026)

## Abstract (arXiv)

Large language model (LLM)-powered agents can translate high-level user intents into plans and actions in an environment. Yet after observing an outcome, users may wonder: What if I had phrased my intent differently? We introduce a framework that enables such counterfactual reasoning in agentic LLM-driven control scenarios, while providing formal reliability guarantees. Our approach models the closed-loop interaction between a user, an LLM-based agent, and an environment as a structural causal model (SCM), and leverages test-time scaling to generate multiple candidate counterfactual outcomes via probabilistic abduction. Through an offline calibration phase, the proposed conformal counterfactual generation (CCG) yields sets of counterfactual outcomes that are guaranteed to contain the true counterfactual outcome with high probability. We showcase the performance of CCG on a wireless network control use case, demonstrating significant advantages compared to naive re-execution baselines.