A new method called probe-and-refine tuning uses synthetic bug-fix probes to iteratively improve repository guidance files with single-shot LLM calls, without agent loops or tool use. On SWE-bench Verified, it achieves a 33.0% mean resolve rate—14.5 percentage points higher than the initial static knowledge base—showing improved coverage rather than patch precision. The method enables agents to use larger step budgets effectively, and performance remains stable across models when diagnostic output is sufficient.
arxiv
arXiv cs.LG
·
51d ago
·
research
Probe-and-Refine Tuning Improves Coding Agent Performance
from English
Importance 3/3
New feature vs. leaders
New harness with differentiators
arXiv cs.LG
Alibaba (Qwen)
Microsoft Research
NVIDIA
AI agents
Code generation
Reasoning models
Related articles
arxiv
arXiv cs.AI
·
51d ago
·
1 view
Finetuning VLA Models Requires Fewer Layers Than Thought
Vision-Language-Action models show severe layer-wise redundancy despite large parameter counts. A training-free compression method using Centered Kernel Alignment removes twin layers, reducing model depth by up to 50% and enabling 40-50% faster training and up to 30% faster inference without performance loss, validated across simulation and real-world robotic tasks.
arxiv
arXiv cs.AI
·
51d ago
SoftSkill: Behavioral Compression for Contextual Adaptation
SoftSkill proposes a method to compress natural-language skills into compact latent priors, improving task performance on SearchQA, LiveMath, and DocVQA. It outperforms SkillOpt by 5.2 to 12.5 points on key benchmarks while replacing hundreds to thousands of Markdown tokens with a few virtual tokens.
arxiv
arXiv cs.AI
·
51d ago
·
3 views
AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning
AutoPass uses runtime and compiler evidence to guide LLM-generated optimization decisions, outperforming expert heuristics and classical autotuning methods. It achieves geometric-mean speedups of 1.043x on x86-64 and 1.117x on ARM64 systems without prior training or fine-tuning.
arxiv
arXiv cs.LG
·
51d ago
·
1 view
Pose6DAug: Physically Plausible Multi-view Object Swapping
Pose6DAug enables robot data augmentation by swapping objects in successful episodes while preserving physically valid 6D pose trajectories. It operates in 3D using a mesh anchored by temporally coherent poses, ensuring multi-view consistency and physical plausibility. Fine-tuning a VLA policy on this augmented data improves novel object success rates by 16.5% over state-of-the-art baselines.
arxiv
arXiv cs.CL
·
51d ago
·
1 view
AgentFinVQA: Auditable, On-Premise Financial Chart QA
AgentFinVQA introduces a multi-agent pipeline for financial chart question answering that ensures auditability and on-premise deployability without significant accuracy loss. It outperforms baseline models by +7.68 pp using a proprietary backbone and +4.84 pp with open-weights Qwen3.6-27B-FP8, while providing a confidence signal via verifier output that improves human review routing.