Software-Engineering

Most “AI builds the app” demos fail exactly where production begins: integration, state, and reliability. A new open-source framework from Databricks—app.build—argues the fix isn’t a smarter model but a smarter environment. The paper formalizes Environment Scaffolding (ES): a disciplined, test‑guarded sandbox that constrains agent actions, validates every step, and treats the LLM as a component—not the system. The headline result: once viability gates are passed, quality is consistently high—and you can get far with open‑weights models when the environment does the heavy lifting. ...

The short of it A new study on SWE-agent working over SWE-bench Verified finds that masking old observations (keeping recent turns verbatim, replacing older tool outputs with a placeholder) often matches or slightly beats prompt-based LLM summarization—and at roughly half the cost. The paper also surfaces a subtle failure mode: summaries can elongate trajectories, encouraging agents to “keep going” when they should stop, diluting efficiency and, at times, performance. Why this matters for builders Most production SE agents (debuggers, PR autoresponders, test fixers) rack up spend on two things: tokens and time. Tool logs dominate both. In practice, observation tokens comprise the bulk of an agent’s turn, so trimming them intelligently is the highest‑leverage knob. The results show you might not need fancy, model‑authored summaries; a rolling “mask” window can land on the most efficient frontier—equal or better solve rate, far lower cost—across Qwen3‑Coder 480B, Qwen3‑32B (thinking/non‑thinking), and Gemini 2.5 Flash (thinking/non‑thinking). ...

The idea of software that writes software has long hovered at the edge of science fiction. But with the rise of LLM-based code agents, it’s no longer fiction, and it’s certainly not just autocomplete. A recent survey by Dong et al. provides the most thorough map yet of this new terrain, tracing how code generation agents are shifting from narrow helpers to autonomous systems capable of driving the entire software development lifecycle (SDLC). ...

When it comes to software development, coding is optional — debugging is inevitable. And yet, most AI code tools today act like overconfident interns: quick to suggest, but clueless when the system breaks. Kodezi Chronos flips that script. Instead of trying to stretch token windows to a million and hoping for the best, Chronos builds an entirely new foundation for debugging: persistent memory, adaptive retrieval, and autonomous iteration. Beyond Token Stuffing: Why Context Windows Miss the Point Large Language Models like GPT-4 and Claude 3 boast massive context windows — 128K, 200K, even a million tokens. But real-world debugging rarely needs to read the whole repository at once. It needs to find the right needle in a messy, multi-decade haystack, then trace its thread through historical commits, CI logs, and edge-case test failures. ...

In the race to build autonomous software engineers, large language model (LLM) agents like Devin and Copilot Chat are lauded for fixing bugs, writing code, and even completing tasks from GitHub issues. But what happens when the code doesn’t even run? That’s the uncomfortable gap SetupBench aims to measure—and the results are sobering. SetupBench introduces a 93-task benchmark evaluating a foundational but under-tested skill: bootstrapping a development environment from scratch. Unlike prior benchmarks that hand agents a fully pre-configured Docker container, SetupBench drops them into a barebones Linux sandbox and challenges them to install dependencies, initialize databases, configure background services, and resolve real-world version conflicts. It sounds simple. It isn’t. ...