Dockerless: Environment-Free Program Verifier for Coding Agents

• URL: http://arxiv.org/abs/2606.28436v1
• Date: Fri, 26 Jun 2026 06:14:55 GMT
• Title: Dockerless: Environment-Free Program Verifier for Coding Agents
• Abstract summary: Dockerless is an environment-free agentic patch verifier that evaluates generated code patches without executing them.<n>On a verifier evaluation benchmark, Dockerless outperforms the strongest open-source verifier by 14.3 AUC points.
• Score: 18.694833759829688
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Program verifiers play a central role in training coding agents, including selecting trajectories for supervised fine-tuning (SFT) and providing rewards for reinforcement learning (RL). Standard execution-based verification requires running unit tests inside per-repository environments such as Docker images, incurring substantial environment setup costs. We propose Dockerless, an environment-free agentic patch verifier that evaluates generated code patches without executing them. Rather than simply matching candidate patches to references, Dockerless judges patch correctness using evidence gathered through agentic repository exploration. On a verifier evaluation benchmark, Dockerless outperforms the strongest open-source verifier by 14.3 AUC points. Using Dockerless as both the SFT trajectory filter and the RL reward enables a fully environment-free post-training pipeline. The resulting model reaches 62.0%, 50.0%, and 35.2% resolve rate on SWE-bench Verified, Multilingual, and Pro, respectively. It surpasses the Qwen3.5-9B baseline by 2.4, 8.7, and 2.9 points, matching environment-based post-training.

Related papers

• Cross-Benchmark Generalization in Long-Horizon Agents [1.0742728354283815]
  We post-train an open-weight mixture-of-experts model on 363 long-horizon Model Context Protocol (MCP) tasks across 27 categories.<n>No externalbenchmark task or grader entered training and no external score informed the reward, training hyper parameters, trained-checkpoint selection, or stopping.<n>Both software benchmarks improve despite the training collection containing no software-engineering tasks.
  arXiv  Detail & Related papers  (2026-07-31T18:05:36Z)
• Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models [49.259951930558]
  Coding agents must integrate external tool returns into ongoing reasoning.<n>We exploit it through function-aware fill-in-the-middle mid-training.
  arXiv  Detail & Related papers  (2026-07-14T07:44:26Z)
• SETA: Scaling Environments for Terminal Agents [49.686781072283814]
  We propose SETA, a scalable framework for generating verifiable terminal environments for reinforcement learning.<n>We release SETA-Env, the largest open-source verifiable terminal RL dataset to date, containing over 4,500 environments.
  arXiv  Detail & Related papers  (2026-07-12T19:40:27Z)
• KAT-Coder-V2.5 Technical Report [61.907486544595336]
  KAT-Coder-V2.5 is a coding-focused agentic model trained to act autonomously inside real, executable repositories.<n>It reconstructs multilingual repositories into sandboxed environments with fail-to-pass and pass-to-pass verification at scale.<n>We further scale reinforcement learning with harness randomization, a reliability-hardened sandbox, an asymmetric actor--critic PPO with hindsight-augmented value estimation, and a harness-oriented reward framework.
  arXiv  Detail & Related papers  (2026-07-06T08:14:02Z)
• LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents [74.07551833809536]
  We introduce LiteCoder-Terminal-Gen, a zero-dependency pipeline that generates terminal training environments directly from domain specifications.<n>Using this framework, we construct two large-scale resources: LiteCoder-Terminal-SFT, comprising 11,255 expert trajectories across 10 domains, and LiteCoder-Terminal-RL, featuring 602 verifiable environments for trajectory-level preference optimization.
  arXiv  Detail & Related papers  (2026-05-28T08:11:57Z)
• CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents [64.53357162213601]
  Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering.<n>But its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards.<n>We present CUA-Gym, a scalable pipeline that co-generates task instructions, environment states, and reward functions.
  arXiv  Detail & Related papers  (2026-05-25T09:28:03Z)
• When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents [32.54888729689753]
  We study failures as a sim-to-real gap in the tool-use partially observable Markov decision process (POMDP)<n>We propose ToolRL-DR, a domain-randomization reinforcement learning (RL) recipe that trains a tool-use agent on perturbation-augmented trajectories.<n>On a 3B backbone, ToolRL-DR-Full retains roughly three-quarters of clean accuracy and reaches an aggregate accuracy comparable to open-source 14B function-calling baselines.
  arXiv  Detail & Related papers  (2026-05-12T10:40:28Z)
• Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning [82.89535601592739]
  We propose a two-stage pipeline that generates reliable base tool-use trajectories through self-evolving synthesis with multi-level validation.<n>These augmentations introduce distractor tools, indirect or ambiguous user queries, and noisy, multi-format, or erroneous tool outputs.<n>This design enables automatic reward computation via reference matching for standard cases and lightweight judge-assisted verification for special behaviors such as error detection.
  arXiv  Detail & Related papers  (2026-04-10T18:38:52Z)
• daVinci-Env: Open SWE Environment Synthesis at Scale [21.291944594753385]
  Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments.<n>We present OpenSWE, the largest fully transparent framework for SWE agent training in Python.<n>OpenSWE is built through a multi-agent synthesis pipeline deployed across a 64-node distributed cluster.
  arXiv  Detail & Related papers  (2026-03-13T14:32:40Z)
• SWE-World: Building Software Engineering Agents in Docker-Free Environments [91.17484806743641]
  SWE-World is a Docker-free framework that replaces physical execution environments with a learned surrogate for training and evaluating software engineering agents.<n>We show that SWE-World raises Qwen2.5-Coder-32B from 6.2% to 52.0% via Docker-free SFT, 55.0% with Docker-free RL, and 68.2% with further TTS.
  arXiv  Detail & Related papers  (2026-02-03T11:44:39Z)
• CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning [57.24524263804788]
  Code verifiers play a critical role in post-verification for LLM-based code generation.<n>Existing supervised fine-tuning methods suffer from data scarcity, high failure rates, and poor inference efficiency.<n>We show that naive RL with only functionality rewards fails to generate effective unit tests for difficult branches and samples.
  arXiv  Detail & Related papers  (2026-01-30T10:33:29Z)
• PIPer: On-Device Environment Setup via Online Reinforcement Learning [74.52354321028493]
  Automated environment setup methods could assist developers by providing fully configured environments for arbitrary repositories without manual effort.<n>Recent studies reveal that even state-of-the-art Large Language Models (LLMs) achieve limited success in automating this task.<n>We combine supervised fine-tuning for generating correct scripts and Reinforcement Learning with Verifiable Rewards (RLVR) to adapt it to the task of environment setup.<n>On EnvBench-Python, our method enables Qwen3-8B (a model runnable on consumer hardware) to perform on par with larger models-Qwen3-32B and GPT-4
  arXiv  Detail & Related papers  (2025-09-29T20:03:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.