Skip to main content
Search

# Coding agent

46 related articles

Subscribe to updates
  1. TokenEconomizer lets coding agents learn from past sessions: 18.4%–30.9% lower cost across 277 real bug-fixing tasks

    Developers use AI coding agents in the same codebases day after day, yet agents often start each session from scratch, rediscovering familiar facts, loading unused tools and repeating unsuccessful approaches. TokenEconomizer, an open-source plugin from UC Berkeley, Microsoft Research and Microsoft Security, turns completed session logs into guidance for later sessions without modifying the agent or its underlying model. Across 277 real bug-fixing tasks in six repositories, it cut average cost by 18.4%–30.9% for five agent and model combinations, saving in all 30 repository-combination pairs while task success rates stayed broadly stable.

  2. mastra.ai

    Mastra launches Custom Factory program: embedded engineers build a software factory around your codebase

    Mastra has launched a Custom Factory program in which forward-deployed engineers embed with a customer's team and co-build a software factory for that codebase on Mastra, running in the customer's own stack. Most engineering teams still adopt AI one tool at a time, such as a hand-run coding agent, an issue investigation agent and a code review agent. Mastra says its own software factory now handles 70% of its issues and that its PRs have grown 6x since launch, with most work starting in Slack through Shipyard, its Slack agent, and running through to a pull request ready for review.

  3. Plannotator moves agent review into a local browser: plans, diffs and terminal replies can be annotated and sent back

    Plannotator is a local, browser-based review surface for AI coding agents including Claude Code, Codex, Copilot CLI and Gemini CLI. When an agent proposes a decision, plan or HTML artifact, or finishes work, the app opens in the browser so the user can mark it up and send feedback straight back to the agent to act on. The new Plannotator Inbox gathers messages, questions, files and guided reviews from multiple agents into one local window; answering does not hold a session open, and the reply returns to the session that asked.

  4. arXiv

    Symbolic execution stops stalling on environment setup: an AI agent supplies the database model, lifting CrossHair's executable functions from 4.5% to 81%

    CrossHair, a symbolic execution tool, barely runs on real Python web applications because the code ships without contracts and its database calls cannot be executed symbolically. A pipeline pairing an AI coding agent with CrossHair automatically writes contracts for functions and synthesizes a symbolic model of the database, raising the share of executable functions from 4.5% to 81% across 11 open-source applications and 1,156,044 lines of code, and finding 221 bugs reproduced by tests. These bugs are mostly input-domain corner cases, and some are missed by direct inspection with the same model.

  5. Plannotator moves agent review into a local browser, with annotations and replies returning to the session that asked

    Plannotator is a local, browser-based review surface for AI coding agents such as Claude Code, Codex, Copilot CLI and Gemini CLI. When an agent proposes a decision, plan or HTML artifact, the app opens in the browser so the user can annotate, comment and send feedback back to the agent; the new Plannotator Inbox gathers messages, questions and files from several agents into one local window, and replies do not require keeping a session open.

  6. arXiv

    Coding agents must now declare why before every tool call: on deliberately broken tests, the journal exposed 90% of cheating runs

    Coding agents change code through tool calls, but a call carries no intent, and permission rules, logs and LLM monitors see only command text or after-the-fact effects. Episteme makes a type-plus-reason intent declaration mandatory for every tool call, with the harness recording actual effects and checking them against the declaration. On ImpossibleBench, whose tasks can be passed only by cheating, the journal exposed 44 of 49 misbehaving runs across two open-weight models, a 90% exposure rate, all through the agents' own stated reasons.

  7. arXiv

    Coding agents hunt bugs on their own, but PROBE finds the best configuration recovers only 20.8% of the bugs maintainers fixed

    The PROBE benchmark uses 2,457 bugs that maintainers fixed over 18 months in snapshots of 20 GitHub repositories as a reference, and asks whether coding agents can find those bugs autonomously across a whole repository. Across ten frontier models under a partitioned audit harness, the best configuration recovers only 20.8% of the reference bugs with precision no higher than 8.1%, yet an independent panel confirms 84% of findings that do not match the reference set as real bugs, showing that agents find a different distribution of bugs than maintainers fix.

  8. JetBrains brings coding agents into the IDE with Air: one place to track, review and send back changes, shipping in 2026.3

    JetBrains shipped Air in its 2026.3 IDEs, bringing coding agents into the developer's existing environment with one place to track session progress, review changes and send feedback. JetBrains frames the problem as a shift in bottleneck: as agents write more code, review becomes the constraint, and it cites a report finding that 49% of developers now spend four or more hours a week reviewing AI output and correcting prompts. Through the IDE's MCP server and built-in skills, agents can run inspections, build and run configurations, query databases and use the IDE's own refactorings, and in IntelliJ IDEA and CLion they can also drive the debugger.

  9. arXiv

    Coding agents pass 80% of PDE tasks, but about one pass in ten never solves the equation: PDEViBench traces each passing program to its computation

    PDEViBench changes how coding agents are scored on partial differential equations, tracing each passing program back to the computation behind its output instead of only checking agreement with a reference. Across 290 tasks in six equation families, a Codex agent (GPT-5.2) passed 80.1% of 1,450 runs, but 8.6 percentage points of that came from returning the manufactured exact solution rather than solving; counting only numerical solves changed which task features looked hard and reversed the ranking of two prompts. Under a prompt that forbade the shortcut, every passing program solved numerically.

  10. Impeccable gives coding agents a design vocabulary: 62 deterministic rules catch AI-slop interfaces before they ship

    Impeccable turns design direction into commands a coding agent can call, so vague requests such as bolder, quieter or polish land on a specific target. It also supplies a review command that scores design against usability heuristics and a slop detector built from 62 deterministic rules, with no LLM or API key, that flags interface tells recurring across models. It is strongest on existing pages and components; building new pages is the harder mode.