# Rethinking Logic Optimization Operators: Theory-Derived Operator Compression via Agentic Source Analysis

arXiv: https://arxiv.org/abs/2607.23672 · HTML: https://mlsanity.com/paper/2607.23672/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 3 of its 31 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 3 of 3)

- [FlowTune: End-to-end Automatic Logic Optimization Exploration via Domain-specific Multi-armed Bandit](https://mlsanity.com/paper/2202.07721/) (2022)
- [DAG-aware Synthesis Orchestration](https://mlsanity.com/paper/2310.07846/) (2023)
- [Provably Good Prim-Dijkstra Revisited: New Theory and a Practical Algorithm for a Classical VLSI Routing Problem with LLMs](https://mlsanity.com/paper/2607.17005/) (2026)

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

- [When Algorithmic Exploration Becomes Cheap: A Case Study of Agentic Research in EDA](https://mlsanity.com/paper/2610.10129/) (2026)

## Abstract (arXiv)

Logic synthesis has evolved from compact two-level minimization to large multilevel flows with many interacting optimization operators. Recent work has invested substantial effort in sequencing these operators: actions are commonly treated as opaque choices in a rapidly expanding search space, while learned circuit representations and heuristic or local-greedy orchestration provide increasingly informed ways to explore it. A central obstacle is the operator vocabulary itself. Production operators are numerous, span different representations and mathematical foundations, and expose behaviors determined by implementation-level guards, bounds, and update order. We address this gap through agentic source analysis, using LLM agents to formulate operator-level relations from pinned ABC and mockturtle implementations and adversarial audits to test their stated scope. The resulting certified relations yield theory-derived operator compression: 40 deployed recipe actions collapse to a 31-action exact Pareto cover, and source-level conditions compile into deterministic admission gates. We integrate these gates directly into ABC Orchestrate to form TACO. Two exact gates reduce Orchestrate runtime by 11% with bit-identical outputs on 66 circuits. In a held-fixed integrated comparison, TACO uses fewer nodes on 14 of 16 circuits, with geometric-mean reductions of 1.0% in nodes and 3.2% in levels, while running 2.6x faster. TACO-max achieves an NDP geometric-mean ratio of 0.903 on HeLO's three exact-input rows.