# Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets

arXiv: https://arxiv.org/abs/2608.08189 · HTML: https://mlsanity.com/paper/2608.08189/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 8 Aug 2026.

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

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Scalable Global Optimization via Local Bayesian Optimization](https://mlsanity.com/paper/1910.01739/) (2019)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [Multi-fidelity Bayesian Optimisation with Continuous Approximations](https://mlsanity.com/paper/1703.06240/) (2017)
- [Conditioning by adaptive sampling for robust design](https://mlsanity.com/paper/1901.10060/) (2019)
- [Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design](https://mlsanity.com/paper/2501.08603/) (2025)
- [Conservative Objective Models for Effective Offline Model-Based Optimization](https://mlsanity.com/paper/2107.06882/) (2021)
- [Symbolic Regression with a Learned Concept Library](https://mlsanity.com/paper/2409.09359/) (2024)
- [Large Language Models as Surrogate Models in Evolutionary Algorithms: A Preliminary Study](https://mlsanity.com/paper/2406.10675/) (2024)
- [EZNAS: Evolving Zero Cost Proxies For Neural Architecture Scoring](https://mlsanity.com/paper/2209.07413/) (2022)
- [Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search](https://mlsanity.com/paper/2405.16450/) (2024)
- [Generative Adversarial Model-Based Optimization via Source Critic Regularization](https://mlsanity.com/paper/2402.06532/) (2024)
- [Language Modeling by Language Models](https://mlsanity.com/paper/2506.20249/) (2025)
- [Scalable Tail Latency Estimation for Data Center Networks](https://mlsanity.com/paper/2205.01234/) (2022)
- [Surrogate Model Assisted Cooperative Coevolution for Large Scale Optimization](https://mlsanity.com/paper/1802.09746/) (2018)
- [Large Language Model-Driven Surrogate-Assisted Evolutionary Algorithm for Expensive Optimization](https://mlsanity.com/paper/2507.02892/) (2025)
- [Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery](https://mlsanity.com/paper/2601.22896/) (2026)
- [Self-Evolving Deep Research via Joint Generation and Evaluation](https://mlsanity.com/paper/2606.04507/) (2026)
- [Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games](https://mlsanity.com/paper/2606.10389/) (2026)
- [DESiRED -- Dynamic, Enhanced, and Smart iRED: A P4-AQM with Deep Reinforcement Learning and In-band Network Telemetry](https://mlsanity.com/paper/2310.18159/) (2023)

## Built on by (most cited first, 3 of 3)

- [AdaEva: Accelerating LLM-Driven Algorithm Design with Adaptive Partial Evaluation](https://mlsanity.com/paper/2610.03896/) (2026)
- [Discovered, Not Designed: Population Evolution for Collaborative and Compute-Intensive Model Discovery](https://mlsanity.com/paper/2610.05950/) (2026)
- [Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems](https://mlsanity.com/paper/2610.16491/) (2026)

## Abstract (arXiv)

LLM-driven program discovery relies on rapid evaluator feedback, but many scientific and engineering tasks require high-fidelity simulations, hardware execution, or physical experiments, making each evaluation expensive. Cheap surrogate evaluators can reduce this cost, yet fixed surrogates are vulnerable to search-induced distribution shift and are difficult to fit reliably from sparse, search-biased labels. We introduce Janus, a framework that uses LLMs to co-evolve target programs and executable proxy evaluators. To address label scarcity, Janus leverages domain knowledge encoded in LLMs to generate task-specific evaluator programs and calibrates them using real outcomes. To mitigate distribution shift, Janus evolves evaluators alongside target programs, selects them using a promotion-aligned objective, and maintains region-conditioned portfolios with online credit updates. Because proxy predictions remain fallible, Janus uses them only to prioritize candidates and requires real validation before candidates can enter the target-program population or update the incumbent. Across five scientific and engineering design tasks, Janus achieves a larger area under the best-so-far improvement curve over the real-evaluation budget and higher final performance than a matched baseline that evolves only target programs. On average, Janus reaches 99/% of the baseline's final improvement with 59.1/% fewer real evaluations. Evolved proxy evaluators also rank promising candidates more accurately than their seed versions. Together, these results extend evaluator-guided LLM discovery from tasks with cheap, scalable feedback to scientific domains where trustworthy evaluation is scarce and expensive.