cloud platform providers

Abstract: ML code should run where researchers choose, not where it was first written. Today, machine learning code mainly lives in two ecosystems, PyTorch on NVIDIA GPUs and JAX on Google TPUs. Migrating repositories between them means building and testing across frameworks and hardware. This migration is (1) a practical need, since it unlocks different hardware for researchers, and (2) a natural benchmark: it involves different frameworks and hardware, covers whole repositories, and is long-horizon and challenging. We introduce XStack, a benchmark that evaluates agents on migrating ML repositories between these two ecosystems. Each agent receives a PyTorch repository and a clean TPU machine and must deliver a JAX repository. Its output passes if it meets our grading criteria, based on the source repository's published result, authenticated and calibrated by us. Migration by agents remains unreliable: Claude Opus 5 passes 75%, GPT-5.6-sol 45%, and every other agent at most 40%. XStack is a step toward freeing ML code from its ecosystem. We release XStack to make progress toward reliable migration across frameworks and hardware measurable.

Abstract: Parameter-Efficient Fine-Tuning (PEFT) has emerged as an important approach for adapting Language Models (LMs) in downstream tasks. However, in the domain of code intelligence, the performance of most PEFT methods relatively drops compared to Full fine-Tuning (FT), hindering their broader applicability. One of the main reasons is that current PEFT methods are generally based on assumptions about the low-rank nature or sparsity of parameter updates, lacking explicit modeling of code-related information. To tackle this limitation, we propose SynMOE, a syntax-aware MOE-guided approach for PEFT on code intelligence learning. Specifically, SynMOE contains two stages: syntactic information extraction and syntax-aware MOE-guided adaptation. It first obtains the syntactic labels of source code from Abstract Syntax Trees (ASTs), and then aligns the labels with the input tokens of code LMs. In the second stage, syntactic labels are integrated into the MOE module, participating in the routing decision of MOE for a more powerful syntactic-aware token representation. We evaluate the effectiveness of the proposed approach by applying it to two typical PEFT methods, LoRA and $(IA)^3$, across three diverse code intelligence tasks. Experimental results show that SynMOE achieves consistent and significant improvements. Even compared to FT, SynMOE achieves comparable or superior performance while being more computationally efficient. In addition, we also conduct ablation studies, hyperparameter analysis, and evaluation in the low-resource scenario to provide a comprehensive investigation of the proposed approach.

Abstract: A multi-step agent task fails when a single tool it needs is missing, yet the tools an agent may need are too many to list: the roughly 8,200 tools on the platform we study have definitions that together exceed the context window of any model we evaluate. We present Tool Recommendation, a deployed system that gives an agent all of them, hundreds of times more than a typical MCP server exposes, through a fixed interface of three tools. It runs at the gateway between agent and tools, executing every call under the end user's own credentials and checking it against the user's consent for each service and the tools the agent may use. We evaluate it on both a public retrieval benchmark and billed end-to-end session cost. On ToolRet, Tool Recommendation places every tool a query needs in the top ten 57% more often than BM25, a lexical ranking that commercial tool search offers, and compares favorably with published systems up to nine times its size. In paired multi-step workflows, its first recommendation covered every required tool in 93% of Codex sessions, and against a fixed list of 100 tools it cut input tokens by 17% with Codex and 40% with Claude Code and the total bill in all 14 runs, by up to 40%, with no change in task completion.