Reinforcement learning (RL) post-training has emerged as a promising paradigm for LLM-based Verilog generation. However, existing RL credit assignment methods are either overly coarse (sequence-level GRPO) or fragmented (line-level methods), leading to severe misattribution as they ignore the characteristics of Verilog designs that are fundamentally structured through concurrent constructs and procedural control flows. To bridge this gap, we propose CirCA, a novel RL framework that performs credit assignment based on Atomic Logic Blocks (ALBs), the smallest semantically complete units of circuit logic. CirCA decomposes Verilog into ALBs, derives reliable rewards from signal-level feedback, and then constructs logic-enhanced signal dependency cones to localize erroneous ALBs, whose localized responsibilities are further incorporated into GRPO through asymmetric advantage correction. Extensive experiments show CirCA establishes a new state-of-the-art across multiple benchmarks among non-reasoning models, and even surpasses some cutting-edge reasoning models on complex tasks.

Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compression paradigms are fundamentally limited by heuristics: heuristic budgeting relies on statistical priors rather than task objectives, causing resource misallocation, while heuristic selection relies on coupled query-key interactions or static inductive biases (e.g., attention sinks). To address this limitation, we introduce LKV (Learned KV Eviction), which formulates KV compression as an end-to-end differentiable optimization problem. LKV integrates LKV-H to learn task-optimized global budgets, and LKV-T to derive intrinsic KV importance without materializing attention matrices. This design bypasses heuristic proxies, strictly aligning compression with task objectives. Extensive evaluations demonstrate that LKV achieves state-of-the-art performance on both LongBench and RULER benchmarks at high compression rates. In particular, on LongBench, LKV achieves near-lossless performance with only 15% KV cache retention, and delivers up to 3.19x decoding throughput gains with negligible (~0.7%) overhead. Crucially, our analysis identifies learned budgeting as the dominant driver of fidelity, demonstrating that data-driven allocation is essential to overcome the limitations of hand-crafted heuristics.

Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing, where excessive modifications overwrite correct code and hinder bug localization. We systematically quantify its impact and introduce precise repair task, which maximizes reuse of correct code while fixing only buggy parts. Building on this insight, we propose PRepair, a framework that mitigates over-editing and improves repair accuracy. PRepair has two components: Self-Breaking, which generates diverse buggy programs via controlled bug injection and min–max sampling, and Self-Repairing, which trains models with Edit-Aware Group Relative Policy Optimization (EA-GRPO) using an edit-aware reward to encourage minimal yet correct edits. Experiments show that PRepair improves repair precision by up to 31.4% under fix₁@1, a metric that jointly considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing, demonstrating its potential for precise and practical code repair.

The attention operator remains a critical performance bottleneck in large language models (LLMs), particularly for long-context scenarios. While FlashAttention is the most widely used and effective GPU-aware acceleration algorithm, it must require time-consuming and hardware-specific manual implementation, limiting adaptability across GPU architectures. Existing LLMs have shown a lot of promise in code generation tasks, but struggle to generate high-performance attention code. The key challenge is it cannot comprehend the complex data flow and computation process of the attention operator and utilize low-level primitive to exploit GPU performance.To address the above challenge, we propose an LLM-friendly Thinking Language (LLM-TL) to help LLMs decouple the generation of high-level optimization logic and low-level implementation on GPU, and enhance LLMs’ understanding of attention operator.Along with a 2-stage reasoning workflow, TL-Code generation and translation, the LLMs can automatically generate FlashAttention implementation on diverse GPUs, establishing a self-optimizing paradigm for generating high-performance attention operators in attention-centric algorithms.Verified on A100, RTX8000, and T4 GPUs, the performance of our methods significantly outshines that of vanilla LLMs, achieving a speed-up of up to 35.16×.Besides, our method not only surpasses human-optimized libraries (cuDNN and official library) in most scenarios but also extends support to unsupported hardware and data types, reducing development time from months to minutes compared with human experts.

Compilers are complex software containing millions of lines of code, taking years to develop. This paper investigates to what extent Large Language Models (LLMs) can replace hand-crafted compilers in translating high-level programming languages to machine instructions, using C to x86 assembly as a case study. We identify two challenges of using LLMs for code translation and introduce two novel data pre-processing techniques to address the challenges: numerical value conversion and training data resampling. While only using a 13B model, our approach achieves a behavioral accuracy of over 91%, outperforming the much larger GPT-4 Turbo model by over 50%. Our results are encouraging, showing that LLMs have the potential to transform how compilation tools are constructed.