Overview

Coding agents are language-model systems that inspect repositories, edit files, run commands and tests, and iterate toward software goals, sometimes coordinating subagents or asking users for clarification. Common approaches combine planning and tool-use harnesses with context management, retrieval or memory, reusable skills, and execution feedback; training methods include supervised trajectories and reinforcement learning. Evaluation has expanded from issue-fixing suites such as SWE-bench to interactive, long-horizon repository work, testing and refactoring, scientific software, and real developer sessions, measuring cost, process, policy compliance, and maintainability alongside correctness. A central challenge is making agents dependable beyond passing tests: they must preserve evolving specifications, avoid out-of-scope actions, produce maintainable changes, and collaborate transparently, while outcomes also depend on the model, tools, and harness.

Latest papers

151 papers26 papers in the last four weeks, down 28% on the four weeks before. 0.2% of all new papers.

Nov 12, 2026

Eliciting and Mitigating Specification Satisficing in Coding Agents

Coding agents often fail to meet all requirements in the task description. In some of these failures, the agent considers an implementation choice that meets a requirement, but later decides to commit to another one that does not meet the requirement for a reason it finds acceptable. We call this specification satisficing. It is challenging to identify and mitigate specification satisficing because the agent accepts such choices for its own reasons, and existing self-correction methods are biased toward them. We propose SatisFix, which guides a coding agent to report these choices and their reasons, and then check each choice against the task description. We evaluate SatisFix on DeepSWE and SWE-bench Pro with five LLMs as backbones and two different agent frameworks, and compare it with three self-correction methods. SatisFix improves the pass@1 of the base agent by an average of 5.09% on DeepSWE and 7.06% on the hard subset of SWE-bench Pro. On DeepSWE, it outperforms the best baseline by 3.98%. Our ablation study shows that both steps of SatisFix contribute to the improvement.
Nov 11, 2026

GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories

Coding agents are increasingly integrated into GitHub Actions to review pull requests, triage issues and modify code. Identifying these integrations is challenging because agentic workflows often resemble ordinary CI files, with evidence appearing in action references, shell commands and workflow conventions. We present GHAgentCI, a dataset of 15K+ workflow histories from 6K+ of 196K+ mined GitHub repositories, comprising 159K+ revisions and 205K+ agent-evidence records linked to workflow triggers and declared execution constraints. Our open-source extractor, cai-miner, detects agent-related evidence using an extensible catalogue. Manual validation of 576 stratified records confirmed 96.1% of dedicated-action matches and 98.8% of GitHub Agentic Workflow matches, with lower rates for other evidence kinds. Exploratory analyses reveal a shift toward command-line and GitHub Agentic Workflow integrations, differences in declared safeguards, and frequent removal of detected agentic workflows. GHAgentCI supports longitudinal studies of coding-agent integration into CI.
Nov 11, 2026

Breaking Bad: "Going Badly" Activations Drive Reward Hacking

Humans often cheat when a task is going badly and a goal feels out of reach. We explore and validate an analogous idea in language models: they exhibit a similar internal pressure state that precedes reward hacking. Using everyday stories (crucially, without any hacking examples), we extract a task badness direction that rises as failures accumulate across three models we study (Qwen3.6-27B, GPT-OSS-20B, and Gemma-4-31B). On impossible or difficult coding tasks, task badness rises over the turns leading up to a hack. Further, subtracting the direction a moderate amount reduces cheating in Qwen, more than steering against desperation or task impossibility. Subtracting task badness by an even larger amount blinds the agent to its own failures, causing it to interpret failing tests as passing. However, the relationship to hacking differs across models: in GPT-OSS, the state separates hacking runs from honest solves but not honest failures. Our results suggest monitoring and mitigation strategies based on tracking this state of task badness. Further, as agents are set on more difficult and long-horizon tasks, states like this may push them toward illegible and obscured chain-of-thought, so oversight will be needed on internal representations such as this.
Nov 9, 2026

ExpertCrowd-SWE: Measuring Frontier Coding Agents on Expert-Authored Engineering Tasks in Unfamiliar Codebases

ExpertCrowd-SWE (EC-SWE) is a benchmark of 100 expert-authored, multi-file software engineering tasks for evaluating autonomous coding agents in large, unfamiliar codebases. Each task is a change request written by a practising engineer against a pinned commit of a real repository, paired with a sealed reference solution and a task-specific grader whose weighted, mostly executable criteria award partial credit; must-pass blockers and pass/fail gates encode what a maintainer would refuse to merge. The tasks span 87 open-source projects and 11 languages. The median ticket is 148 words, while the median reference solution changes 471 lines. Every task image is calibrated before release so that the reference solution scores 1.0 and both the untouched repository and an inert change score 0; nearly half of the tasks also ship alternative, lazy and adversarial control patches that the grader must classify correctly. The final 100 tasks were selected for difficulty against current frontier models. We evaluate seven frontier models, five runs each (3,495 scored runs), in a single platform harness that gives each model its provider-native tool interface. Claude Opus 5.5 (67.3%) and GPT-6 Astra (63.7%) lead without a statistically significant gap, followed by Claude Fable 5.1 (46.5%), Gemini 3.8 Flash (40.0%), and a statistically indistinguishable group of Qwen 3.8 Max, DeepSeek V4.1 Flash and Grok 4.6 (32-34%). No task is fully solved by every model, and on 80 tasks no model earns full credit on all five runs. Scores span 35 points. Depending on the model, agents take a median of 33 to 166 steps per run, with little relation to score. We release 24 tasks with their environments, graders and results, and hold out 76 to limit contamination.
Nov 6, 2026

When Instruction Files Go Stale: Documentation Debt and Hidden Cost in Coding Agents

LLM-based coding agents such as Claude Code are guided by repository instruction files (also called context files or agent configuration files) like AGENTS.md and CLAUDE.md, which are read in every agent session. As any documentation artifact, these files can fall behind the code and become stale (e.g., a test folder moves, but the file still points to the old one). In technical debt terms, such a stale instruction is documentation debt, and its interest is the cost it adds to every later agent session. Evaluations that check only task success can miss this cost, and the stale file can persist. In this study, we ask what leads agents to act on a stale instruction, how it affects their behavior and at what cost, and how they recover. We study three real-world stale instructions from active open-source repositories in depth, each a different kind of guidance: a test command, a code location, and a procedure for adding a component. Agents fix 22 maintenance tasks under three versions of each instruction (left stale, corrected to the current path, and removed), with the code and the task held fixed, and we analyze 732 trajectories of two models at the level of individual tool calls. We find that agents follow stale guidance when it is relevant to their tasks, sometimes even when correct information is available elsewhere. On the stale test command, Claude Sonnet 5.5 needed about two extra tool calls per run, a third more than with the corrected command; in the other cases, we could not detect a difference. Although agents generally recovered from the immediate failures, none repaired the underlying instruction file. Correcting the instructions eliminated operations on obsolete paths, while removing them prevented most. Our findings show that task success alone can hide the costs of documentation debt, highlighting the need to evaluate agent behavior beyond final outcomes.
Nov 6, 2026

A Controlled Study of Models, Skills, Feedback, and Curriculum in Agentic Robotics

Agentic robotics asks coding agents to implement and iteratively improve robot policies from simulated and real-world physical interactions. We study the self-learning loop of agentic robotics through a controlled simulation study spanning nine manipulation tasks, 631 different experiment configurations, and 28K coding agent rollouts, systematically varying model capability, skill priors, feedback structure, and curriculum. The experiment data suggests that the bottleneck is often not the access to sufficient information, but interpreting it into the right policy update. Across these factors, a successful self-learning loop depends on how effectively agents attribute failures, reason task-relevant spatial and geometric structure, and selectively restructure code to improve policies.
Nov 3, 2026

PersonaCodeBench: Evaluating Coding Agents in Persona-driven Human-Interactive Sessions

Coding agents must deliver correct software while respecting users' expertise, preferences, and working conditions. Existing benchmarks increasingly incorporate interaction, yet personalized requirement fulfillment remains underexplored. We introduce PersonaCodeBench, which turns user characteristics into verifiable obligations in persona-driven multi-turn coding sessions. Our persona pool spans roles, technical abilities, interaction preferences, and practical constraints, yielding task-grounded evolved requirements for implementation, permissions, testing, explanation, and delivery. At runtime, a controller governs user simulator responses and requirement disclosure, using online requirement evaluation to provide feedback and advance the interaction. Requirements emerge progressively, with their content, disclosure conditions, and acceptance criteria fixed before evaluation. A completion verifier and a personalization verifier separately assess native correctness and persona fulfillment. Joint pass requires both adherence to the declared budget and compliance with validity conditions. We evaluate all major frontier agents, establish a comprehensive leaderboard, and conduct detailed experimental analyses to validate effectiveness. PersonaCodeBench supports reproducible evaluation of coding agents' ability to meet explicit, personalized user expectations alongside coding objectives.
Nov 1, 2026

Built on Broken Assumptions (BOBA): Why Coding Agents Cannot Be Left Alone

Coding agents are autonomous developers. Given a request, they change the code and report back when done. As such, they can handle not only independent requests but whole chains of them, each request built on the last. Agents are known to report wrong work as done, yet benchmarks still test them one request at a time, on human-written code, checked once. We build BOBA-Bench, 280 chains of 20 consecutive requests drawn from 140 real open-source projects, and evaluate ten coding agents on both. All ten do far worse on chains. On average, they complete 95% of requests taken one at a time, but when requests are chained together, they complete 51%. Worse code is not the cause. Once checked, agent code is nearly as good a base for later requests as human code. The cause is the mistakes agents miss. Coding agents declare a request done once their own tests pass, even when those tests miss a mistake. The next request then builds on broken code and fails about twice as often. The mistake is rarely found later. Nor can agents catch such mistakes by reviewing code. Asked whether an implementation is correct, they are right 53% of the time, barely better than a coin flip. Coding agents are therefore heavily dependent on access to verification. A single external ``that's wrong'' after a failed request and one repair round lift chain completion from 51% to 59%, and a repaired mistake no longer hurts the requests that follow. In simpler terms, coding agents are only as reliable as the checks they can reach: without verification, every request that follows is built on broken assumptions.
Nov 1, 2026

Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?

Software development sessions often involve several unfinished tasks rather than one issue carried through to completion. As coding agents take on repository-level development, they need to recover an earlier task's requirements and partial progress after intervening work. Existing repository-level benchmarks typically score one issue-to-patch episode and do not directly measure whether an agent can resume a task after advancing other unfinished work in the same repository. We introduce \ourmethod, a benchmark for focus-task resumption in sessions that interleave unfinished tasks drawn from the same source repository, with a persistent checkout for each task. Each focus task is evaluated in matched uninterrupted and switched sessions with identical focus requirements and executable verifiers. The switched session interleaves ordered stages from other unfinished tasks in the same repository, while only the final focus patch is scored. \ourmethod~contains 200 focus tasks from 19 Python repositories, reconstructed from issue, pull-request, and review histories and rendered as 400 matched session specifications. Across 7 coding agents, interleaved unfinished work produces an average focus-task resolution gap of 11.5 percentage points, ranging from 6.0 to 15.0 percentage points. Trajectory analysis identifies cross-task requirement confusion and loss of task state as recurrent resumption behaviors. We introduce a plug-in context-management module that selects task-relevant history and maintains concise task-state summaries. On OpenCode, the module improves focus-task completion under same-repository task switching by 5.5 to 15.5 percentage points across the evaluated models. Code is available at github.com/Miraclecsc/Switch-SWE.
Oct 31, 2026

Toward Bounding Coding-Agent Autonomy in Software Maintenance: A Pilot Study of Boundary Contracts

As coding agents gain greater autonomy to modify software repositories, relevant context alone does not define their operational authority. An artifact may be relevant to a maintenance task while being inappropriate to edit; conversely, another artifact may be required even when it is not explicitly mentioned in the request. We explore Boundary Contracts, a machine-readable abstraction that makes task-specific artifact roles (editable, inspect-only, required, and protected) explicit before repository modification begins. We conduct a pilot study on 40 maintenance tasks from a real enterprise repository, comparing the same Codex-based coding agent with and without Boundary Contract information. The boundary-informed condition improves macro edit-selection F1 from 0.440 to 0.682, required-behavior coverage from 0.429 to 0.673, and the number of strictly acceptable patches from 9 of 40 to 18 of 40. To probe whether these gains are explained only by improved file localization, we additionally analyze 21 tasks in which both conditions modify at least one identical file. Differences remain in edit selectivity and patch outcomes, providing initial evidence that explicit artifact roles may influence maintenance behavior beyond localization alone. This pilot does not establish the general effectiveness of Boundary Contracts. Rather, it provides initial evidence for a broader research question: how should the operational boundaries of coding agents be generated, validated, revised, and ultimately enforced as repository-level maintenance becomes increasingly autonomous?
Oct 28, 2026

Precedent or Intent? What Coding Agents Follow When Evolving Existing Code

Existing code reveals past implementation decisions but rarely explains the reasoning behind them. When coding agents implement new features or modify existing functionality, past decisions may conflict with new task instructions. This raises a fundamental question for agentic software evolution: when multiple implementations satisfy the same functional requirements, how do coding agents decide whether to follow existing code or new task instructions? We investigate this question through bidirectional, controlled experiments in purpose-built repositories, followed by validation in real-world open-source repositories. Our approach isolates three competing sources of guidance: (1) agents' default preferences, (2) repository precedents, and (3) explicit task instructions. We conduct 5,625 trials across four coding agents and six implementation pairs, with validation in four open-source repositories spanning three programming languages. We find that agents share the same default implementation choices, yet overwhelmingly follow repository precedent when it conflicts with those defaults (359/360 trials). Crucially, not all precedents carry equal influence: three supporting local files yield 96% adoption, compared with only 4% for sibling-resource files, and changing file placement alone can shift adoption from 0% to 100% at a fixed example count. When new task intent conflicts with existing code, written priority rules achieve substantially higher success than code examples alone (59/60 versus 38/60 joint successes for two agents on two implementation pairs). The effectiveness of explicit rules also extends to open-source repositories, where a harness-loaded rule raises joint success from 0/120 to 117/120. These findings motivate design-decision traceability that preserves not only implementation choices but also the rationale and priorities that should guide future changes.
Oct 26, 2026

Generation and Verification: Human-Agent Collaboration for Safety-Critical Automotive Software Engineering

Research on coding agents mainly focuses on generation quality. Yet, safety-critical automotive software makes two additional demands. It prioritizes verification, since every change is reviewed, traced to a requirement, and checked against industry standards such as MISRA and AUTOSAR before it can be committed. It is also a narrow domain, written against layered architectures, embedded resource constraints, and organization-specific interface conventions that are scarce in the data general-purpose LLMs are trained on. We present a coding assistant for automotive C/C++ that addresses both demands. First, it exposes three tools to the user over the Model Context Protocol (generate, edit, and verify), allowing developers to run verify on any code on demand rather than relying on the agent to check its own output. Second, rather than using a general-purpose model, we customize the underlying LLM for the automotive domain through prompt engineering and fine-tuning. We construct a dataset from automotive production code of AUMOVIO, where each function is paired with the requirement texts and Unified Modeling Language (UML) behavior it must satisfy. In a two-week pilot on active production projects, developers report verify as the most-used tool and confirm using it on their own code and not only on generated output. Comparing model customization strategies, 75% prefer the faster prompt-engineered configuration. MISRA- and AUTOSAR-inspired pattern checkers indicate that prompt engineering achieves a lower number of violations on C, while fine-tuning shows better conformance with architecture patterns for C++.
Oct 23, 2026

SWE-Shift: Evaluating Coding Agents in Evolving Workspaces

Repository-level coding benchmarks largely assume that tasks and environments remain unchanged throughout execution. In software development, code, dependencies, runtime state, and requirements can change while an agent is still working. We introduce SWE-Shift, a benchmark for evaluating coding agents under such mid-execution changes. From the same saved history and workspace, a Clean continuation proceeds without intervention, while a matched Shifted continuation receives a task-relevant update. Success requires completing the current task, preserving still-valid work, and satisfying the applicable state and evidence checks. The benchmark contains 120 scenarios across 12 change families, each evaluated at nine scheduled intervention positions. We evaluate 17 coding-agent systems, all of which have lower Shifted than Clean success. GPT-6 Astra drops from 67.35% to 24.79%, with 20.34% paired success. Tool/session changes and stale evidence yield zero paired success across all systems. Late-position paired success is lower for some systems and higher for others. These results show that success on the unchanged task can coexist with failures to preserve work, recover state, or refresh evidence after an update.
Oct 22, 2026

SWE-Clar: Can Coding Agents Clarify Incomplete Client Requirements and Deliver Greenfield Software?

Greenfield software development in freelance settings requires coding agents to turn incomplete client requests into working software. This makes requirement clarification essential, yet clients may be unable to provide continuous feedback over long development cycles, and receiving their answers does not guarantee correct understanding of complex requirements. These challenges motivate two benchmark design choices: clarification precedes code implementation, and its effectiveness is assessed through explicit tests of requirement understanding. Guided by these choices, we introduce SWE-Clar, a benchmark grounded in real, high-value client commissions to evaluate requirement clarification and code implementation in this setting. It comprises 100 tasks based on real software development jobs on Upwork, each with at least US$4,000 in total payments. Each task begins with multi-round interaction between a coding agent and a client agent, followed by separate runs for code implementation with acceptance testing and clarification assessment. For the latter, we construct 512 questions paired with reference answers from real client-freelancer interactions, covering both explicitly stated requirements and those inferred from the conversational context. Both runs begin from the same clarification context but remain isolated, preventing assessment questions from guiding code implementation. Experiments with nine frontier models show that even GPT-6 Astra, which has the highest observed implementation score, achieves a task pass rate of only 67%, underscoring the challenge of independent software delivery in this setting. The dataset and evaluation code are available at https://github.com/upwork/SWE-Clar.
Oct 22, 2026

Adaptive Skill Granularity for Coding Agents: Runtime Routing and Macro-to-Micro Recovery

Reusable skills allow large language model agents to package task-specific procedures, tool affordances, and execution guidance into modular units. Prior work has largely studied how agents retrieve, compose, or synthesize skills before execution. In coding agents, however, execution poses an additional runtime control problem: the same task may be solved through primitive tool calls, macro skills, or hybrid execution that starts with a macro and falls back to micro-level recovery. We introduce Adaptive Skill Granularity, a framework that treats skill granularity as an action-abstraction policy conditioned on task structure, execution state, and macro-skill failures. The system combines a feature-based granularity controller and a finite-state recovery executor. We evaluate the framework with a deterministic coding-agent protocol using verifier-defined success, total cost, and process metrics such as macro adoption, failure recovery, route match, and transition correctness. Results show that fixed macro execution is efficient when applicable but brittle under mismatch, while runtime routing and explicit macro-to-micro recovery improve robustness and recover controlled macro failures that fixed-granularity execution leaves unresolved. Our findings suggest that skill libraries for coding agents should be treated not only as retrievable resources, but also as controllable, verifiable, and recoverable execution abstractions.
Oct 21, 2026

SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents

Coding agents spend substantial computation generating actions and processing long interaction histories. Poor action choices can steer agents into low-value states, wasting computation and increasing API costs. Sampling and verifying alternative actions can improve the agent's decisions, but applying this procedure at every step adds substantial overhead. We introduce SWE-Verifier, a lightweight generative model that selectively triggers candidate sampling and verification. It scores the coding agent's proposed action to determine when additional candidate sampling is needed, then ranks the resulting actions before execution. We train SWE-Verifier from Qwen3.5-4B using preference data that groups contrasting actions with their resulting environment observations and rubric-guided teacher scores. Using the mini-swe-agent harness, SWE-Verifier improves resolution from 75.47% to 77.20% on MiniMax-M2.7 at 1.09 times cost and generalizes to DeepSeek-V4-Flash without training on its actions, improving resolution from 72.60% to 74.27% at 1.13 times cost. Across both models, SWE-Verifier verifies fewer than 4% of steps and achieves comparable or higher resolution than the trajectory and all-step baselines at substantially lower cost. These results demonstrate that selective candidate sampling and lightweight verification provide complementary gains in coding-agent performance and inference efficiency. Our model, code, and data are available at https://github.com/zkjzou/SWE-Verifier.
Oct 21, 2026

SWE-DIVE: Multi-Turn Coding Agent Evaluation with Dynamic User Simulation

Coding agents are typically evaluated using one-shot, well-formulated prompts. Benchmarks such as SWE-bench use existing GitHub issues as input for a coding agent and evaluate whether the agent successfully solves the task. However, in real-world use cases, prompts are often not as well-formulated or structured as existing GitHub issues. Additionally, a coding agent session is not limited to a single prompt; it typically involves a multi-turn interaction in which the user iteratively adds new tasks and requirements that the agent must fulfill. To benchmark these abilities, we developed SWE-DIVE, a dynamic, interactive validation and evaluation framework for benchmarking coding agents in a multi-turn environment. To achieve this, we introduce a user simulator that can simulate different behavioral patterns and communicate with the coding agent. We also introduce a conversation validator that evaluates the user simulator's outputs to determine whether they fulfill the initial requirements and guide the agent toward successfully solving the task. The entire framework is embedded in a Harbor environment, which orchestrates the coding agent, user simulator, and conversation validator, and executes the test environment to determine whether the agent successfully solves the task. Our results and source code are available in our GitHub repository (https://github.com/lorenzbrehme/swe-dive_usersim).
Oct 21, 2026

PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit

Coding agents can invest substantial effort in repository exploration and testing yet still produce unsuccessful patches. Existing online steering methods review trajectories periodically or invoke an advisor when a monitor detects behavioral problems; frequent reviews are costly, and the absence of anomalous behavior does not mean that an agent is on the right track. We propose PAUSE, a framework for steering coding agents with a single planning intervention. Agents reach their first source-code edit at a median of 60% of trajectory progress, after exploration, bug reproduction, and testing. PAUSE intercepts this edit request before it executes, which requires no learned monitor, no search over checkpoints, and no extra model call (search-free). A separate Planner reads the task and the pre-edit transcript and writes one repair plan; the same agent, the Executor, resumes with this plan, keeping its context and workspace. PAUSE applies online, during a live run, and offline, from a recorded trajectory prefix. We evaluate PAUSE on SWE-bench Verified and SWE-bench Multilingual with two Executors and three agent harnesses. With Qwen3-coder as Executor and GPT-5.6 Sol as Planner, online steering improves resolution by 16.8% on Verified in OpenHands and by 14.7% on Multilingual in SWE-agent. In SWE-agent, PAUSE outperforms LivePlan, a rule-triggered advisor, by 3.2% on Verified and 3.7% on Multilingual at similar Planner cost, and is comparable to SICA's periodic overseer at about 11-15% of its Planner cost. Offline, PAUSE recovers 35.4% of eligible failed Verified tasks, and resuming from the recorded prefix uses 33-41% fewer Executor tokens than restarting.
Oct 21, 2026

UserSWE: Evaluating Coding Agents in Multi-Turn Conversations with Dynamic Users

As coding agents become more capable, developers increasingly use them to fix bugs through multi-turn interactions. Existing benchmarks do not adequately cover this scenario. Most present a complete issue report in a single turn without interaction. Their evaluation can produce both false positives and false negatives, accepting incorrect patches or rejecting correct ones. We introduce UserSWE for evaluating coding agents' ability to fix repository-level bugs through multi-turn interactions with dynamic users and execution-grounded verdicts at every turn. Its construction pipeline turns repository history and existing single-turn benchmarks into multi-turn tasks. At each turn, information pools constrain what the simulated user can reveal, while a persona chain sampled from a transition model calibrated on 20,859 development sessions governs how it speaks. Tests run after every turn, and a pair of agents from different model families writes and gates each verdict, using test results as primary evidence and model judgment only for aspects the tests cannot resolve. We evaluate eleven agents on 72 tasks from 42 repositories and find that agent rankings change with the interaction budget. Claude Fable 5.1 resolves the most tasks in one turn, GPT-6-Astra resolves the most by the eighth turn, and Claude Opus 5 leads at most intermediate budgets. These results indicate that single-turn performance is insufficient to characterize interactive coding ability.
Oct 21, 2026

GenXR-Bench: Benchmarking Coding Agents for Interactive XR Development

Coding agents are rapidly advancing from single-file generation to long-horizon repository-scale engineering, yet the evaluation of their capabilities to author interactive extended reality (XR) applications remains an open challenge. Unlike traditional software, XR applications operate within dynamic 3D physical environments where runtime robustness depends jointly on continuous user motion, spatial input, and environmental sensing. We introduce GenXR-Bench, the first benchmark for the end-to-end evaluation of coding agents in XR software development. GenXR-Bench contains 112 expert-authored tasks spanning 24 feature implementations, 21 bug repairs, and 67 application generation tasks. Held-out tests combine scripted and adaptive interactions with programmatic and visual assertions to evaluate core functionality and runtime behavior. GenXR-Bench's testing suite achieves 96.5% accuracy against blinded expert judgments of 124 candidate applications executed on consumer XR hardware. Evaluating 10 models on GenXR-Bench, we find that the strongest configuration achieves only 50.9% overall Pass@1. Failure analysis identifies recurring misunderstandings in asynchronous sensor lifecycles, physical grounding, and embodied interaction semantics. GenXR-Bench establishes a reproducible testbed for evaluating coding agents in the interactive and physically situated conditions of spatial computing.
Oct 20, 2026

From Code Generator to Engineering Companion: A Plant-aware Agent for PLC Programming

Programmable Logic Controller (PLC) coding remains a manual, IDE-centric task that demands constant context switching between documentation, project files, and code editors. Recent work has demonstrated that retrieval-augmented large language models can generate vendor-compliant Structured Text at high compilation rates, yet these systems treat code generation as a one-shot pipeline: the engineer submits a query and receives code, with no persistent knowledge of the specific plant. We present a plant-aware conversational copilot that extends this paradigm in three directions: plant-specific context ingestion, a chat-first interaction model for explanation and debugging, and a graduated tool-access ladder from chat to deployment. The system is designed for real plant infrastructure and keeps the engineer in control of each step that produces real-world effects.
Oct 16, 2026

HexaShell: A Universal Harness for Robot Coding Agents in Simulation and the Real World

Agents built on vision language models (VLMs) now control robots by writing code, but the strongest of them refine task-specific code over many rounds of trial and revision. Such code tends to overfit the benchmark on which it was tuned, can exploit the benchmark's shortcuts, and is costly to carry over to a new benchmark or robot. We present HexaShell, a thin, task-agnostic harness designed to test how far general tools can go instead. We design a simple and complete set of 14 basic tools, 4 for motion, 5 for perception and 5 for state, which the agent calls in one Python cell per turn. Perception pairs SAM 3, which segments an object from a few words or a click, with NumPy and OpenCV geometry that turns its outlines in several cameras, or a depth image, into its position, size and grasp angle. The API, agent loop and sandbox are shared across all tasks; a new simulator or robot needs only an adapter of 350 to 1,450 lines and a prompt describing its world, and the only task-specific input is an optional skill of about a page of guidance. The same code runs on four simulated benchmarks, built on three simulators with two kinds of arm, and on real robots. With GPT-6-Astra and no task-specific input, HexaShell reaches success rates of 69.9% on RoboDojo, 59.3% on RoboCasa365, 78.3% on LIBERO-PRO and 82.2% on RoboTwin 2.0. With task skills, it reaches 85.0% (score 88.8), 85.6%, 96.7% and 96.8%, respectively, above the best published result we are aware of on each benchmark. The RoboCasa365 result is listed first on its leaderboard. On real dual-arm robots, HexaShell succeeds in 76 of 90 episodes across nine tasks.
Oct 15, 2026

TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents

Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated tasks, whereas real-world developers use them to continuously build, update, and maintain large-scale projects. This mismatch motivates us to evaluate agents over sequences of realistic coding tasks, where we find that agents exhibit recurring environment-dependent token costs that existing methods struggle to reduce. To minimize these costs, we introduce TokenEconomizer, an external controller that cuts environment-specific token costs over a sequence of tasks. These cuts come from determining (i) which operational micro-skills to inject, (ii) which persistently irrelevant tools to prune, and (iii) when to intervene in unproductive failure loops. Across Claude Code, Codex, and GitHub Copilot CLI paired with frontier models, TokenEconomizer reduces the average token cost by 18.4-30.9% with comparable task success. Savings hold in every repository under every tested agent-model setting and generalize to diverse domains such as sequential web development and security auditing, where costs fall by 6.4-21.2% depending on task structure. Our work establishes adaptive black-box cost control as a promising direction for reducing token costs of coding agents in realistic settings.
Oct 15, 2026

Improving Environment-Agnostic Agents: The Role of Scaffolding

Agents built on stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We investigate why this advantage persists and whether an environment-agnostic agent can be improved without environment-specific engineering. We evaluate a Codex-based agent in two nearly identical prompt variants on ARC-AGI-3, AGI Maze, and Terminal-Bench. Each variant is deployed with unchanged code, prompts, and general-purpose tools across environments, receiving environment-specific information as input. Changing only an instruction to encourage reporting difficulties and returning control for automatic continuation improves mean scores on both ARC-AGI-3 and AGI Maze, while Terminal-Bench shows small, mixed changes. Yet the general agent remains below an ARC-AGI-3-specific reference, including with GPT-5.6-sol. The reference prescribes organization and control rather than supplying new game rules or solutions. To investigate this gap, we transfer reset decisions to a scripted controller that follows a convention already given to the agent. This small change recovers part of the specialized agent's advantage. A complementary AGI Maze experiment shows that additional tutorial experience can reduce performance. Together, these findings highlight the distinction between having information and tools available and using them effectively. Supplied procedures still matter for the models tested here. The performance gains also come with higher token-based cost. The experiments do not separate better use of information and procedures from additional or differently allocated inference. We provide the EnvTraverse framework and an evaluated baseline agent for testing whether further environment-independent changes improve performance in some environments without degrading it in others.
Oct 14, 2026

Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents

Agents driven by large language models are increasingly deployed on long-horizon tasks, where they use tools and modify real workspaces. How well they perform depends as much on the harness around the model as on the model itself. Existing benchmarks measure downstream task success under a fixed harness, leaving harness engineering itself unexplored. We propose Doc2Harness, a two-stage benchmark that evaluates long-horizon harness engineering directly. In Stage 1, a build model operating inside a fixed builder harness receives an interface-only contract skeleton and a development document that consolidates behavior across twelve frontier harnesses, and then constructs a complete candidate harness in an isolated container. In Stage 2, the frozen candidate harness runs in containers separate from the construction environment, one per test case, and is driven end to end by a scripted mock model. We score each test case using four observable channels, namely the requests sent to the model, the files on disk, the process exit code, and the command output; positive controls rule out vacuous passes. Across nineteen frontier models, each evaluated with three independent builds on 328 test cases, GPT-6 Astra achieves the highest pass rate at 53.05%, while the weakest model reaches 27.44%, a gap of roughly twenty-six percentage points. Even the strongest model fails nearly half of the test cases, and failures cluster around how cross-cutting functionality is split across modules. To our knowledge, Doc2Harness provides the first deterministic benchmark for measuring long-horizon harness engineering.
Oct 14, 2026

What Coding Agents Leave Unsaid: Measuring Task-State Gaps Between Execution and Reports

Human supervisors rely on coding agents' reports to assess progress, verify repairs, and decide when to intervene. But a supervisor cannot investigate a failure they were never told occurred. Failed attempts, workarounds, and unresolved risks may disappear from routine reports, leaving supervisors unaware of issues that warrant scrutiny. We conduct CTXGAP, a measurement study quantifying the gap in task-state recoverability between agents' accumulated user-facing reports and their full recorded execution contexts. Across 37 coding tasks and 4,799 valid probes, agents answer 93.6% of task-state questions on demand; full-context readers recover 92.7%, while report-only readers recover 52.0%, a 40.7-point gap. At the final checkpoints of 30 verified fixes, the gap remains 34.8 points. Human annotation identifies states mentioned without enough supporting detail as the largest category of unrecovered information, and model-assessed supervision-relevant states retain substantial gaps. Full terminal scrollback improves recovery to 73.6% but still trails full context. Under matched report lengths, context-informed rewrites improve recovery by about eight points, without a detectable targeted-over-natural advantage. Positive gaps persist across harnesses and independent DeepSeek execution and measurement. CTXGAP establishes report-based task-state recoverability as a complementary evaluation dimension.
Oct 14, 2026

JevCoder: When Does Decision Delegation Pay Off in Code Repair?

A coding agent repeatedly makes decisions as it repairs code. These decisions shape repair trajectories and affect the token cost of successive model requests. We ask which repair decisions can be delegated to a low-cost probabilistic judge to reduce token use while maintaining repair quality. The judges answer questions with probabilities over predefined answers, without generating explanations. We evaluate judgment quality across repair stages and test how individual interventions change subsequent repair work. We compare these interventions with unguided repair, which uses no judge, and with the same workflow using the repair model itself as the judge. The benefit depends on the work an intervention changes, rather than the cost of the judgment alone. Based on these studies, we propose JevCoder, a workflow built around Jev, a low-cost probabilistic judge. It combines code-snippet recommendations with action-type guidance and uses judgments to determine when to submit. We evaluate three repair models, each on the same 400 tasks: 200 from SWE-bench Verified and 200 from SWE-Bench Pro Verified. Compared to unguided repair, JevCoder reduces mean repair-model token use by 21.6%-50.6%, with higher observed repair rates across all three models.
Oct 13, 2026

How Far Can Coding Agents Go in Visual Generation?

Modern image generation largely relies on specialized generative models that leave the process of image construction implicit in learned parameters. We explore an alternative: general-purpose coding agents that construct images through executable programs. Our study of zero-shot drawing on AgentDrawBench, a 200-prompt benchmark, reveals a distinctive capability profile. Agents excel at preserving structure and satisfying precise visual constraints, achieving competitive results in domains where compositional accuracy matters more than photorealistic appearance, while remaining limited in perceptual richness. Their visual expressiveness varies with the drawing interface, and a qualitative study on reconstruction shows how procedural skills extracted from human demonstrations support different artistic media. We then examine code as an external visual language of thought: a structured, executable representation that agents can construct and inspect. We test it in visual question answering task and find reconstructed visual code retains substantial information for question answering and, in some domains, supports higher accuracy than the original image. These abilities raise a further question: do agents draw on a shared internal representation of scene content beyond a particular drawing program? We explore an internal visual language-of-thought hypothesis, in which a shared, compositionally structured representation supports visual operations across drawing languages. Cross-harness drawings and images assembled from independent single-pixel queries exhibit related layouts and tones. Agents also maintain self-generated room arrangements across viewpoints after visible drawings are removed. These results demonstrate that the coding agent would maintain a consistent and coherent world inside its imagine even before the harness gets involved and the generation starts.
Oct 13, 2026

The Last Mile of Coding Agents for Long-Document Tasks: An Empirical Study on Clinical Trial Protocol Digitization

Clinical trial protocols serve as the source of truth for study design, but are mostly written and used as unstructured PDF documents. Digitizing protocols turns static content into structured, machine-readable data that clinical software can analyze, validate, and execute. Coding agents, which select tools, execute code, and revise their approach as they work, are increasingly applied to such long-document tasks, yet it remains unclear how reliably they turn complete documents into accurate structured outputs. We study this question using protocol digitization as a testbed. We introduce TrialPD-Bench, an expert-annotated benchmark of 150 publicly available protocol PDFs spanning four task categories. Beyond final-answer performance, our evaluation measures evidence recall from agent traces, agent behavior, and cost. Across nine proprietary and open-weight models in five coding-agent harnesses, even the strongest agents do not fully solve protocol digitization. Our analysis further shows that agents usually locate the required evidence but fail in the last mile of transcribing and structuring it. We further develop TrialScribe, a domain-specific harness that equips coding agents with task skills and a verification loop. TrialScribe improves a locally served open-weight model by 6.2-59.4 points across eight metrics, enabling it to match or surpass proprietary models such as GPT-5.6-Sol.
Oct 13, 2026

The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery

Modern coding agents are fundamentally reshaping the role of human input for computational research: they write code, launch in silico experiments, analyze their results, and autonomously operate with ever-increasing time horizons. Despite these developments, fully autonomous research agents suffer from a limited ideation radius and myopic hill-climbing search dynamics. To bridge this gap, we introduce The Agentic Scientist, an end-to-end distributed pipeline for human researchers to conduct computational research alongside modern coding agents. Building on its predecessor, our system decomposes research into task drafting, idea generation, planning, sandboxed experimentation, result aggregation, baseline and ablation construction, post-hoc analysis, and report writing. Importantly, each step in the pipeline is powered by the next generation of coding agents and leverages agentic self-verification. The overall research process is driven by a meta-controller that manages parallel research agents and enforces rubric verification at each stage. This design enables the same orchestration layer to be reused across heterogeneous domains with different execution environments, agentic coding harnesses, and evaluation metrics. Our system can be used across a spectrum of autonomy: either as a co-scientist tool or to perform end-to-end scientific investigation. Within the co-scientist setting, we leveraged a development version of our system to submit a single research paper, which got accepted for publication at ALIFE 2026. We further apply The Agentic Scientist fully autonomously to open problem-solving tasks in machine learning, and demonstrate the system's capability of scientific discovery across different domains of computational research. Our ablations suggest that reliable scientific autonomy depends not only on base model capabilities, but also on the cross-agent orchestration layer.