arXiv AI
Aug 6
COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation
arXiv:2608. 04336v1 Announce Type: cross Abstract: Code generation systems make each LLM call with a model, a prompt, and decoding settings.
FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines
arXiv:2606. 19605v1 Announce Type: cross Abstract: Multi-step LLM pipelines fail through interactions among retrieval, reasoning, and formatting steps, so prompt-only optimization can miss bottlenecks in the chain.
Related stories
arXiv AI
Jun 11
APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection
arXiv:2606. 11459v1 Announce Type: cross Abstract: Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential.
arXiv AI
Aug 12
RLMOpt: Adaptive Prompt Optimization via Recursive Language Models
arXiv:2608. 10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization procedure: the algorithm determines which candidates to explore and how the search progresses, while the language model generates or refines prompt proposals.
arXiv AI
Jul 9
Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1
arXiv:2607. 06764v1 Announce Type: new Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures.
arXiv AI
Aug 3
Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation
arXiv:2604. 05150v2 Announce Type: replace-cross Abstract: We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation.
arXiv AI
1d ago
Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline
arXiv:2608. 16187v1 Announce Type: cross Abstract: AI-assisted development tools generate vulnerable code at significant rates, yet few automated mechanisms exist to detect, enrich, fix, and verify security issues at development velocity, particularly ones that ground remediation in real-world threat context.
arXiv AI
Jun 4
Bilevel Autoresearch: Meta-Autoresearching Itself
arXiv:2603. 23420v2 Announce Type: replace Abstract: If autoresearch is itself a form of research, then autoresearch can be applied to research itself.
arXiv AI
1d ago
ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
arXiv:2602. 15983v3 Announce Type: replace-cross Abstract: Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk: code that executes and returns solver-feasible solutions may encode semantically incorrect formulations---a feasibility--correctness gap reaching 90 percentage points on compositional problems.
arXiv AI
Jun 11
GPO: Learning from Critical Steps to Improve LLM Reasoning
arXiv:2509. 16456v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks.
arXiv Machine Learning
Jul 23
Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance
arXiv:2607. 19386v1 Announce Type: new Abstract: Cross-paper comparison of sparse autoencoder (SAE) interpretability often relies on autointerpretability scores.
arXiv AI
Jul 23
PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization
arXiv:2607. 19653v1 Announce Type: cross Abstract: Large language model (LLM) agents now perform well on correctness-oriented repository-level tasks, including SWE-Bench issue resolution and feature implementation in real codebases.
arXiv AI
Jun 2
PBT-Bench: Benchmarking AI Agents on Property-Based Testing
arXiv:2605. 15229v3 Announce Type: replace-cross Abstract: Existing code benchmarks measure whether an agent can produce any test that reproduces a known bug, or whether it can produce a patch that fixes a described issue.