# ATLAS-RTC: Closing the Loop on LLM Agent Output with Token-Level Runtime Control

arXiv: https://arxiv.org/abs/2603.27905 · HTML: https://mlsanity.com/paper/2603.27905/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 12 of 12)

- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation](https://mlsanity.com/paper/2403.06988/) (2024)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [CRANE: Reasoning with constrained LLM generation](https://mlsanity.com/paper/2502.09061/) (2025)
- [Towards Verifiably Safe Tool Use for LLM Agents](https://mlsanity.com/paper/2601.08012/) (2026)
- [ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction](https://mlsanity.com/paper/2508.00500/) (2025)
- [RvLLM: LLM Runtime Verification with Domain Knowledge](https://mlsanity.com/paper/2505.18585/) (2025)
- [The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding](https://mlsanity.com/paper/2603.03305/) (2026)
- [Adaptive Focus Memory for Language Models](https://mlsanity.com/paper/2511.12712/) (2025)
- [VIGIL: A Reflective Runtime for Self-Healing Agents](https://mlsanity.com/paper/2512.07094/) (2025)

## Abstract (arXiv)

We present ATLAS-RTC, a runtime control system for autoregressive language models that enforces structured output during decoding. ATLAS-RTC monitors generation at each step, detects drift from output contracts using lightweight signals, and applies targeted interventions such as biasing, masking, and rollback. Unlike post-hoc validation or static constrained decoding, it operates in a closed loop, enabling correction before errors materialize. Across structured generation and tool-calling tasks, ATLAS-RTC improves first-attempt success rates by 20 to 37.8 percentage points, with up to 88% latency reduction in failure-dominated settings. Results show that many failures arise from decoding artifacts rather than task misunderstanding, motivating runtime control as a distinct layer in LLM systems.