AIBullisharXiv – CS AI · Jun 237/10
🧠Researchers developed a small critic model that guides large code agents during execution rather than evaluating completed work, reducing computational costs while improving performance. The approach achieves 25.2% accuracy on SWE-bench Verified at 64% lower expense than larger agents, demonstrating that supplementing agent training with efficient feedback mechanisms outperforms scaling alone.
🏢 Hugging Face
AIBullisharXiv – CS AI · Jun 117/10
🧠CRANE is a training-free parameter-editing method that merges paired Instruct and Thinking model checkpoints to create superior code agents. By selectively combining reasoning capabilities from Thinking models with the tool-discipline of Instruct models, CRANE achieves significant performance gains—66.2% pass rate on Roo-Eval (+19.5%) and resolves 14 additional instances on SWE-bench—while maintaining computational efficiency.
AIBullisharXiv – CS AI · Jun 17/10
🧠Researchers introduce Clean-PR, a training methodology that leverages 2 million real-world GitHub pull requests to improve AI models' ability to perform repository-level code editing. The approach achieves significant performance gains on SWE-bench benchmarks without relying on complex agent scaffolding, demonstrating that code editing capabilities can be effectively internalized into model weights through high-quality training signals.
AIBullisharXiv – CS AI · May 127/10
🧠Researchers introduce M2A, a novel model merging paradigm that combines mathematical and agentic reasoning in large language models without retraining. The approach improves a Qwen3-8B model's software engineering benchmark performance from 44.0% to 51.2% by strategically injecting mathematical reasoning capabilities along directions that preserve agent behavior.
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers demonstrate a methodology for translating a large production Rust codebase (648K LOC) into Python using LLM assistance, guided by benchmark performance as an objective function. The Python port of Codex CLI, an AI coding agent, achieves near-parity performance on real-world tasks while reducing code size by 15.9x and enabling 30 new features absent from the original Rust implementation.
AIBullisharXiv – CS AI · Mar 56/10
🧠Researchers propose a new framework called Critic Rubrics to bridge the gap between academic coding agent benchmarks and real-world applications. The system learns from sparse, noisy human interaction data using 24 behavioral features and shows significant improvements in code generation tasks including 15.9% better reranking performance on SWE-bench.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers evaluated whether structural codebase indexing improves coding agent performance by running controlled experiments with Claude Opus 4.7 across standardized benchmarks. Results show the index significantly improves code localization and task resolution rates without increasing costs, and outperforms simpler retrieval baselines, suggesting structural ranking becomes valuable for multi-file code changes.
🧠 Claude🧠 Opus
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce CICL, a decision-aware context layer that improves how language model agents select and compress relevant information for tool use. By scoring evidence based on action criticality and packing high-utility data as typed memory cards, the system achieves significant performance gains on code retrieval benchmarks, raising hit rates from 58% to 78% on SWE-bench tasks.
🧠 GPT-5
AIBullisharXiv – CS AI · Jun 56/10
🧠Researchers introduce FuseSearch, an AI system that optimizes parallel code localization by reducing redundant tool invocations from 34.9% to near-zero through adaptive execution strategies. The approach combines supervised fine-tuning and reinforcement learning to dynamically adjust search breadth, achieving state-of-the-art performance on SWE-bench while using 68.9% fewer tokens and delivering 93.6% speedup.
AINeutralarXiv – CS AI · May 126/10
🧠BoostAPR is a new AI framework that improves automated program repair by using dual reward models and reinforcement learning to identify which code edits actually fix bugs. The system achieves significant improvements on multiple benchmarks, including 40.7% on SWE-bench Verified, demonstrating that more granular feedback mechanisms can substantially enhance AI's ability to repair software vulnerabilities.
AINeutralarXiv – CS AI · Apr 146/10
🧠A large-scale empirical study of 679 GitHub instruction files shows that AI coding agent performance improves by 7-14 percentage points when rules are applied, but surprisingly, random rules work as well as expert-curated ones. The research reveals that negative constraints outperform positive directives, suggesting developers should focus on guardrails rather than prescriptive guidance.
AINeutralOpenAI News · Feb 236/105
🧠SWE-bench Verified, a popular coding evaluation benchmark, is being discontinued due to increasing contamination and flawed testing methodology. The analysis reveals training data leakage and unreliable test cases that fail to accurately measure AI coding capabilities, with SWE-bench Pro recommended as the replacement.
AIBullishOpenAI News · Aug 135/105
🧠SWE-bench Verified is being released as a human-validated subset of the original SWE-bench benchmark. This new version aims to provide more reliable evaluation of AI models' capabilities in solving real-world software engineering problems.
