arXiv:2608. 06410v1 Announce Type: new Abstract: Automated agent design improves agent harnesses through iterative revision, evaluation, and feedback summarization.
arXiv:2607. 12605v1 Announce Type: cross Abstract: Large language models (LLMs) have improved automated program repair (APR), but two limitations remain.
The paper presents a systematic analysis of five state‑of‑the‑art automated program repair agents, tracing their decision‑making across 500 real‑world repair tasks. It finds that while the agents perform well on simple fixes, they struggle with logic‑intensive bugs, often producing verbose, overfitted patches that pass tests without addressing root causes. Key bottlenecks identified include poor test generation, limited regression test selection, and reliance on primitive tooling without access to debuggers or advanced program analysis tools.
arXiv:2608. 04682v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) are increasingly adopted in software engineering (SWE) scenarios, capable of fixing a specific bug in large-scale codebase.
arXiv:2607. 15854v1 Announce Type: cross Abstract: Coding agents can fix a failing example without preserving the domain rule that made it fail, so later generations can repeat the same plausible mistake.
arXiv:2609.32490v2 Announce Type: replace Abstract: LLM-based multi-agent systems (MASs) have shown strong potential for solving complex tasks, but most assume that task requirements are sufficiently...
arXiv:2608. 06701v1 Announce Type: cross Abstract: Fixing GitHub issues in large-scale projects is a long-horizon task, especially when a fix requires changes across multiple locations or the issue description lacks the information needed to localize and repair it.
arXiv:2603. 23129v4 Announce Type: replace Abstract: G\"odel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop.
arXiv:2608.23041v1 Announce Type: new Abstract: LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interactions and lead to overall task failure...
arXiv:2606. 19787v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents for multi-step tasks in executable environments, yet their ability to perform realistic operations research (OR) work remains unclear.
arXiv:2603. 23129v3 Announce Type: replace Abstract: G\"odel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop.
Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many failures into typed recovery signals, but broad language-agent tasks often expose only a coarse task failure.
arXiv:2607. 18859v1 Announce Type: new Abstract: While Large Language Models have greatly advanced automated issue resolution, existing agent-based methods exhibit a fundamental limitation in their insufficient exploration of repair strategies.