The Dual-State Architecture for Reliable LLM Agents

TL;DR

This paper introduces the Dual-State Architecture and DSAP primitive to enhance the reliability of LLM code generation agents by combining stochastic outputs with deterministic verification, improving success rates.

Contribution

It formalizes the DSAP primitive, proposes a three-level recovery hierarchy, and demonstrates significant reliability improvements across multiple LLMs and diagnostic benchmarks.

Findings

Reliability gains of up to 66 percentage points at 1.2-2.1x baseline cost.

100% context injection effectiveness in recovery scenarios.

Step-specific recovery effectiveness varies, with 37.5% for test generation.

Abstract

Large Language Models deployed as code generation agents exhibit stochastic behavior incompatible with the deterministic guarantees required by software engineering. We formalize the Dual-State Action Pair (DSAP), an execution primitive that couples stochastic generation with deterministic post-condition verification. Guard functions act as sensing actions that project opaque LLM outputs onto observable workflow state, enabling a dual-state decomposition: finite, deterministic S_workflow paired with infinite, stochastic S_env. We prove that for epsilon-capable generators, failure probability P(fail) <= (1-epsilon)^R_max -> 0. To prevent naive O(R^K) retry explosion across multi-step workflows, we introduce a three-level recovery hierarchy: context refinement (retry within step), informed backtracking (stagnation detection with cascade invalidation and context injection to upstream steps), and human escalation. Experimental validation across 13 LLMs (1.3B-15B parameters) on three diagnostic probes demonstrates reliability gains of up to 66 percentage points at 1.2-2.1x baseline cost. Recovery mechanism evaluation on 99 SWE-Bench Pro instance-arm pairs (Qwen3-Coder-Next) demonstrates 100% context injection effectiveness (upstream output changed in all 71 escalation events) with step-specific recovery asymmetry -- 37.5% for test generation vs. 0% for patch generation -- and 0% end-to-end patch production, establishing the boundary between execution architecture and plan synthesis: execution recovery is necessary but not sufficient for autonomous software engineering.