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.