6arXiv cs.AI (Artificial Intelligence)·
Claude Opus 4.7 generates competitive trapped-ion quantum shuttling compilers, cutting development time from months to days
Researchers demonstrate that Claude Opus 4.7 (and a second model, Claude Fable 5) can autonomously generate and iteratively refine full Python shuttling compilers for trapped-ion quantum computers from written specifications alone. The LLM-generated compilers reduce shuttling timesteps by up to 76% versus hand-crafted state-of-the-art compilers on linear traps and up to 39% on junction traps, with no additional manual algorithmic engineering. The study covers three progressively complex trap architectures and benchmarks against a common quantum circuit suite. The key finding is that frontier LLMs can compress compiler development timelines from several months to a few days for new quantum hardware architectures.
Related guides (4)
Related events (8)
MLIR-based compilation method for LLM inference on specialized hardware
Researchers present an MLIR-based compiler pipeline for deploying large language models on AI accelerators, using two dialect layers (TopOp for framework-agnostic graph representation and TpuOp for hardware-specific lowering). The method splits each Transformer layer into three static compilation stages (prefill, prefill_kv, decode) to handle the distinct computational profiles of prompt processing and autoregressive generation. The approach is implemented in the open-source TPU-MLIR compiler and LLM-TPU project, supporting Qwen, Llama, InternVL, and MiniCPM-V families with GPTQ, AWQ, and AutoRound quantization.
Frontier coding agents use metaprogramming to handle esoteric programming languages
A new arXiv paper evaluates six LLM-based coding agents on four esoteric programming languages (including Brainfuck and Befunge-98), finding that the strongest agents—Claude Opus 4.6 and GPT-5.4 xhigh—often avoid writing the target language directly, instead generating it via Python metaprograms. Forbidding this strategy causes large performance drops, and text guidance alone does not transfer the capability to weaker models, though sharing Opus-derived Python helper code does sharply improve mid-tier agents. The study reveals capability stratification that mainstream benchmarks like SWE-Bench Verified compress into narrow bands, suggesting frontier agents succeed by constructing and debugging working models of unfamiliar environments rather than pattern-matching to training data.
LLM-guided search framework discovers new quantum LDPC code families via structured concept evolution
Researchers introduce Structured Concept Evolution (SCE), a framework pairing an LLM with an algebraic mutation grammar to discover lifted-product quantum LDPC code families. The system evolves structured algebraic specifications rather than asking the LLM to design codes from scratch, enabling discovery of both abelian and non-abelian code families competitive with standard designs like bivariate-bicycle codes. Results are achieved using lightweight models (GPT-5.4-mini and GPT-5.4-nano), suggesting LLM-guided combinatorial search can be effective for hard discrete design problems in quantum error correction.
Cursor's Composer 2.5 rivals GPT-5.5 and Claude Opus 4.7 on coding benchmarks at lower cost
Cursor released Composer 2.5, a specialized agentic coding model built on Moonshot's Kimi K2.5 open weights with additional pretraining and reinforcement learning fine-tuning tailored to Cursor's own CLI harness. The model ranks third on the Artificial Analysis Coding Agent Index behind Claude Opus 4.7 and GPT-5.5 at max reasoning, but significantly undercuts them on cost ($0.44 vs $4.14 per task) and speed (6.7 vs 17.7 minutes). The training approach—co-optimizing model and harness together using synthetic tasks, text feedback during RL, and 25x more synthetic data than Composer 2—illustrates a specialist model strategy that challenges the dominance of generalist frontier models in coding workflows.
Anthropic Releases Claude Opus 4.5 with State-of-the-Art Coding, Agent, and Computer Use Capabilities
Anthropic has released Claude Opus 4.5, positioning it as the best model in the world for coding, agentic workflows, and computer use, with pricing reduced to $5/$25 per million input/output tokens. The model demonstrates significant token efficiency gains—up to 65% fewer tokens than prior models on equivalent tasks—alongside improvements in long-horizon autonomous task execution, multi-step reasoning, and self-improving agent behavior. The release is accompanied by updates to Claude Code, the Claude Developer Platform, and integrations with Excel, Chrome, and desktop environments. Early partner feedback from GitHub Copilot, Cursor, Notion, Warp, and others reports measurable benchmark improvements and new use cases previously out of reach.
ADAPT-GQE: Generative AI framework learns to synthesize quantum chemistry circuits, demonstrated on real hardware
Researchers introduce ADAPT-GQE, a generative AI pipeline that trains transformer models on ADAPT-VQE reference circuits to synthesize ground-state preparation circuits for quantum chemistry, then uses reinforcement learning to push accuracy beyond the training data. The approach achieves order-of-magnitude speedups in circuit generation relative to ADAPT-VQE while maintaining comparable or improved accuracy. The system is demonstrated on imipramine (a tricyclic antidepressant) and executed on Quantinuum Helios-1 quantum hardware, marking a milestone for AI-generated quantum chemistry circuits on state-of-the-art hardware.
Agentic Proving for Program Verification: Claude Code Achieves 98.1% on CLEVER Benchmark
Researchers evaluate Claude Code in an agentic proving framework on CLEVER, a Lean 4 benchmark for verifiable code generation, achieving 98.1% end-to-end success on program generation and verification over self-consistent entries. The system generates valid specifications for 98.8% of problems and certifies implementations against ground-truth specifications for 87.5% of problems. The results reveal a growing mismatch between existing program verification benchmark difficulty and modern agentic prover capabilities, motivating calls for more rigorous evaluation methodologies. The findings support compiler-in-the-loop agentic paradigms as the current state-of-the-art for foundational program verification.
Anthropic Introduces Claude Opus 4 and Sonnet 4 with Leading Coding Benchmarks and Agent Capabilities
Anthropic has released Claude Opus 4 and Claude Sonnet 4, positioning Opus 4 as the world's best coding model with 72.5% on SWE-bench and 43.2% on Terminal-bench, and Sonnet 4 at 72.7% on SWE-bench. Both models are hybrid (near-instant + extended thinking), support extended thinking with tool use in beta, parallel tool execution, and improved memory via local file access. Alongside the models, Anthropic is launching Claude Code as generally available with GitHub Actions, VS Code, and JetBrains integrations, plus four new API capabilities: code execution tool, MCP connector, Files API, and one-hour prompt caching. Pricing is unchanged from prior Opus and Sonnet tiers ($15/$75 and $3/$15 per million tokens respectively), with availability on Anthropic API, Amazon Bedrock, and Google Cloud Vertex AI.