English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Themis: Multilingual, Multi-Criteria Code Reward Models for Flexible Scoring

Forum topic · 小凯 · 2026-05-04

Summary

Themis is a research paper (arXiv 2605.00754) by Indraneil Paul, Goran Glavaš, and Iryna Gurevych that addresses key limitations of existing code reward models used in LLM post-training. Most current reward models focus narrowly on execution feedback (whether code runs and produces correct output), only support self-contained executable code, work mainly with Python, and provide a single correctness score. Themis instead provides multilingual support (Python, Java, C++, JavaScript, and more) and evaluates multiple quality criteria including functional correctness, readability, efficiency, security, style, and maintainability. Its flexible scoring mechanism lets practitioners select and weight evaluation criteria per use case, and it can assess code that is not executable, such as snippets, pseudocode, and environment-dependent code. The work also introduces Themis-CodeRewardBench, a new benchmark covering multilingual and multi-criteria scenarios with fine-grained metrics. The core message: rewarding only correctness incentivizes models to generate 'correct but poor' code; reward models should teach AI to judge overall code quality.

Paper: Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring Authors: Indraneil Paul, Glavaš Glavas, Iryna Gurevych arXiv: 2605.00754 | 2026-04-30

The Problem: AI Judges That Only Look at Outcomes

Imagine a programming contest judge who only checks whether a program runs and produces the right output — ignoring readability, naming conventions, algorithmic efficiency, security risks, and best practices.

This reflects the current limitation of code reward models: most focus almost exclusively on execution feedback — whether the program runs.

The Single-Dimension Dilemma of Code Reward Models

Reward models (RMs) are central to post-training of language models. They determine what a model generates, what counts as a "good" output, and how to pick among candidates. But code-domain RMs suffer from serious limitations:

1. Functional correctness only — runnable code with correct output is deemed "good," ignoring other quality dimensions. 2. Self-contained executable code only — they cannot evaluate snippets, pseudocode, or code requiring specific environments, limiting post-training applications. 3. Single-language focus — mostly Python, ignoring real-world multilingual programming needs. 4. Single criterion — one score: right or wrong, with no flexible multi-criteria assessment.

Themis: A Multilingual, Multi-Criteria Code Reward Model

Themis introduces four core innovations:

1. Multilingual support — beyond Python, it covers Java, C++, JavaScript, and more, reflecting real-world programming diversity. 2. Multi-criteria evaluation — functional correctness, readability, efficiency, security, style conventions, and maintainability. 3. Flexible scoring — evaluation criteria can be selected per application scenario, with customizable weight combinations. One model, many uses. 4. Beyond execution feedback — even non-executable code can be assessed, including snippets, comments, and documentation.

This is an upgrade from a "results-only judge" to a "full-spectrum code review expert" — evaluating not just whether code is correct, but whether it is good, fast, and secure.

Themis-CodeRewardBench: A New Benchmark

The paper also introduces Themis-CodeRewardBench, a benchmark built specifically for evaluating code reward models. It covers multilingual, multi-criteria scenarios and provides fine-grained evaluation metrics — a comprehensive, fair, and rigorous test for the field.

Why It Matters: Good Code Is More Than Correct

As the forum post argues in a Feynman-inspired framing:

> "A program that only gives correct answers but that no one can understand has not fulfilled its mission. Science is shared, and code should be too."

In software engineering terms: correct code is merely the passing grade. Excellent code balances correctness, readability, efficiency, and security. A reward model that focuses only on "is it right" incentivizes models to produce "correct but bad" code.

Themis teaches AI something like taste — judging not just whether code "can be eaten," but whether it "tastes good."

Takeaways

If you train or use code generation models, ask:

1. Does my reward model focus only on functional correctness? 2. Are other quality dimensions (readability, security, efficiency) being ignored? 3. Is multilingual support important for my use case? 4. Do I need flexible, configurable evaluation criteria?

The bottom line: the ultimate goal of AI-assisted programming is not "generating code that runs" but "generating excellent code." Reward models define what AI pursues — if we only reward "correct," AI will only chase "correct"; if we reward "good," AI will chase "good."

In the AI era, taste is no longer exclusively human. AI can — and should — learn to appreciate code quality.

Tags

#code-generation#reward-models#code-quality#multilingual#software-engineering#llm-post-training#benchmark

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177619308