Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning

• URL: http://arxiv.org/abs/2606.06835v1
• Date: Fri, 05 Jun 2026 02:21:41 GMT
• Title: Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning
• Abstract summary: We learn a policy that decides when to translate from reward alone, developing language- and domain-adaptive introspection.<n>We analyze how tool use emerges over training, per language and per domain.
• Score: 25.323183334678195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The performance gap across languages in LLMs is well documented, and closing it natively requires pretraining or fine-tuning on corpora that, for most languages, do not exist. Translation offers an alternative: converting an input into the model's dominant language unlocks its full capabilities at once. Applying translation to every input, however, is wasteful for languages the model already handles, while leaving the choice to the model fails in the opposite way, as LLMs are overconfident and skip the tool even when they cannot understand the input. Prior work resolves this with language-specific rules, domain heuristics, language identifiers, or external routers, each requiring manual engineering. We instead learn a single policy that decides when to translate from reward alone, developing language- and domain-adaptive introspection that assesses its own comprehension and invokes translation only when it cannot solve a task natively. Using data built by our answer-preserving translation pipeline, we continue RL on the post-trained Qwen3-4B across 22 languages in 3 resource tiers (High, Low, XLow) and 5 domains, and introduce confidence-gated GSPO for cost-sensitive tool use. The gated policy lifts reward over the baseline by +4.6 on High, +23.5 on Low, and +17.5 on XLow. Against an unconstrained policy that almost always translates, it preserves full reward at 63% of the cost and is Pareto-optimal across 87% of the cost-sensitivity range. Additionally, to simulate behavior on a completely unseen language, we create 2 synthetic languages, where our gated policy improves +18.7 over the overconfident baseline that underutilizes the tool even on these incomprehensible inputs. The policy transfers zero-shot to 9 held-out languages, and we analyze how tool use emerges over training, per language and per domain.

Related papers

• Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision [41.68344013253776]
  We introduce HumanEval-X++, an execution-based benchmark that extends HumanEval-X to a broad many-to-many language space.<n>On HumanEval-X++ and existing benchmarks, it yields consistent gains over the untrained baselines.<n>Our study establishes a reliable approach of data generation, training, and benchmarking, paving the way toward further bootstrapping the quality of many-to-many translation for programming languages.
  arXiv  Detail & Related papers  (2026-08-14T00:56:41Z)
• Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation [0.8602553195689513]
  Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages(LRPLs) such as Julia.<n>We propose a three-phase pipeline that resolves this trilemma by decoupling syntax acquisition from algorithmic reasoning.<n>Applying to Qwen3-8B, our pipeline improves pass@1 by up to +7.6 points on MultiPL-E and +14.2 points on the Agnostics LiveCodeBench for Julia compared to SOTA results.
  arXiv  Detail & Related papers  (2026-07-08T09:18:56Z)
• Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language [9.529147118376464]
  Python outperforms PyLang by up to 19% across all configurations.<n>Models possess language-agnostic understanding but cannot express it in an unfamiliar language.
  arXiv  Detail & Related papers  (2026-05-15T04:37:31Z)
• LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them? [3.809788214307542]
  We identify and characterize two key failure modes: the multilingual transfer bottleneck and the language consistency bottleneck.<n>We extend logit lens analysis to track language probabilities layer by layer and compute cross-lingual semantic similarity of hidden states.<n>This is the first approach to leverage layer-localization of language control for efficient multilingual adaptation.
  arXiv  Detail & Related papers  (2026-01-27T19:38:12Z)
• Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters [53.59868121093848]
  We introduce Seed-X, a family of open-source language models (LLMs) with 7B parameter size.<n>The base model is pre-trained on a diverse, high-quality dataset encompassing both monolingual and bilingual content across 28 languages.<n>The instruct model is then finetuned to translate by Chain-of-Thought (CoT) reasoning and further enhanced through reinforcement learning (RL) to achieve better generalization across diverse language pairs.
  arXiv  Detail & Related papers  (2025-07-18T03:19:43Z)
• LLM-Driven Multi-step Translation from C to Rust using Static Analysis [27.122409727034192]
  Translating software written in legacy languages to modern languages, such as C to Rust, has significant benefits in improving memory safety.<n>We propose SACTOR, an LLM-driven C-to-Rust zero-shot translation tool using a two-step translation methodology.<n>SACTOR produces more natural and Rust-compliant translations compared to existing methods.
  arXiv  Detail & Related papers  (2025-03-16T14:05:26Z)
• Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment [50.27950279695363]
  The transfer performance is often hindered when a low-resource target language is written in a different script than the high-resource source language. Inspired by recent work that uses transliteration to address this problem, our paper proposes a transliteration-based post-pretraining alignment (PPA) method.
  arXiv  Detail & Related papers  (2024-06-28T08:59:24Z)
• ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters [29.211715245603234]
  We tackle the problem of zero-shot cross-lingual transfer in NLP tasks via the use of language adapters (LAs) Training target LA requires unlabeled data, which may not be readily available for low resource unseen languages. We extend ZGUL to settings where either (1) some unlabeled data or (2) few-shot training examples are available for the target language.
  arXiv  Detail & Related papers  (2023-10-25T06:22:29Z)
• Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer [92.80671770992572]
  Cross-lingual transfer is a central task in multilingual NLP. Earlier efforts on this task use parallel corpora, bilingual dictionaries, or other annotated alignment data. We propose a simple yet effective method, SALT, to improve the zero-shot cross-lingual transfer.
  arXiv  Detail & Related papers  (2023-09-19T19:30:56Z)
• Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models [67.19567060894563]
  Pretrained Language Models (PLMs) learn rich cross-lingual knowledge and can be finetuned to perform well on diverse tasks. We present a new study investigating how well PLMs capture cross-lingual word sense with Contextual Word-Level Translation (C-WLT) We find that as the model size increases, PLMs encode more cross-lingual word sense knowledge and better use context to improve WLT performance.
  arXiv  Detail & Related papers  (2023-04-26T19:55:52Z)
• Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT [129.99918589405675]
  We present an effective approach that reuses an LM that is pretrained only on the high-resource language. The monolingual LM is fine-tuned on both languages and is then used to initialize a UNMT model. Our approach, RE-LM, outperforms a competitive cross-lingual pretraining model (XLM) in English-Macedonian (En-Mk) and English-Albanian (En-Sq)
  arXiv  Detail & Related papers  (2020-09-16T11:37:10Z)
• Inducing Language-Agnostic Multilingual Representations [61.97381112847459]
  Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world. We examine three approaches for this: (i) re-aligning the vector spaces of target languages to a pivot source language; (ii) removing language-specific means and variances, which yields better discriminativeness of embeddings as a by-product; and (iii) increasing input similarity across languages by removing morphological contractions and sentence reordering.
  arXiv  Detail & Related papers  (2020-08-20T17:58:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.