IR2Solve replaces iterative LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → repair loops with one semantic call that emits a schema-constrained ModelIR, followed by deterministic verification and IR-to-solver compilation - no search, no multi-agentUsing several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.Full definition → workflow.
The IR writes sets, parameters, variables, objectives and constraints as restricted Python-like expressions, and expands finite per-index constraint families into individual scalar entries, cutting free-index and implicit-quantification errors.
Cost result: 1 call per instance vs 8 for Chain-of-Experts and 39 for SAC-Opt, which burn 3.3x and 22.9x its tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → volume - while staying competitive on objective correctness across six benchmarks.
An ablation on 153 IndustryOR/ComplexLP instances shows sequential gains from the structured IR interface, the scalar-constraint instruction, and deterministic verification.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Shows that replacing iterative multi-agent repair loops with a single structured intermediate representation plus deterministic verification can match or beat prior systems while cutting token cost by over 20x — a pattern applicable to other LLM-to-code/structured-output pipelines, not just optimization modeling.
Key quotes
“We present IR2Solve, an intermediate-representation-first autoformulation pipeline that uses a single semantic LLM call to produce a schema-constrained ModelIR, followed by two deterministic stages: verification and IR-to-solver compilation.”
“On a matched ten-instance cost panel, IR2Solve uses one semantic call per instance, whereas Chain-of-Experts and SAC-Opt use 8 and 39 calls per instance and consume 3.3 and 22.9 times the token volume of IR2Solve, respectively.”
articleAre the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon StatementsXinke Tong, Xuanming Zhang, Tianyi Tang, An Yang, Jiatu Hu, Guojie Lin, Zhenzhen Shi, Lingfeng Zeng, Boyu Yang, Bing Zhao, Hu Wei, Lin Qu, Dayiheng Liu
postWhat Happened When I Applied Karpathy's Autoresearch Idea to LLM InferenceManthan Gupta
articleCost-Effective Automated Judging of Natural-Language Mathematical ProofsBenjamin Grayzel