KAT-Coder-V2.5 Technical Report

• URL: http://arxiv.org/abs/2607.05471v1
• Date: Mon, 06 Jul 2026 08:14:02 GMT
• Title: KAT-Coder-V2.5 Technical Report
• Abstract summary: 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.
• Score: 61.907486544595336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real, executable repositories rather than as a single-turn code generator. Its capability is bottlenecked less by model scale than by the scarcity of reproducible environments, verifiable rewards, and high-value trajectories, which we address with an end-to-end agentic post-training framework. AutoBuilder reconstructs multilingual repositories into sandboxed environments with fail-to-pass and pass-to-pass verification at scale, from which we regenerate self-contained task specifications, recover near-miss trajectories, and distill supervision through process-aware filtering, while KwaiClawEnv synthesizes large-scale tool-use trajectories from executable services and real task seeds. 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, and unify SWE, Agent-Claw, and WebCoding experts via Multi-Teacher On-Policy Distillation. Across six software-engineering and agentic benchmarks, KAT-Coder-V2.5 delivers the best agentic tool-use result on PinchBench and ranks second only to the frontier Opus 4.8 on repository-level software engineering. Our service is available at https://streamlake.com/product/kat-coder.

Related papers

• A Jagged Frontier: Evaluating Robustness of Code Agents to Semantics-Preserving Transformations [7.48361039542955]
  We evaluate whether coding agents that repair repository-level issues remain reliable when the surrounding code variations is rewritten into a semantically equivalent form.<n>We introduce a random variant sampler that applies common semantics-preserving transformations (SPTs)<n>We evaluate two agentic scaffolds (mini-SWE agent and OpenCode) each backed by one of four frontier models.
  arXiv  Detail & Related papers  (2026-08-18T23:46:11Z)
• EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL [54.09410318521061]
  We introduce EnvFactory, a fully automated framework for Agentic Reinforcement Learning (Agentic RL) training.<n>EnvFactory autonomously explores and stateful, executable tool environments from authentic resources.<n>It synthesizes natural multi-turn trajectories through topology-aware sampling and calibrated refinement.<n>It achieves superior training efficiency and downstream performance, improving Qwen3-series models by up to +15% on BFCLv3, +8.6% on MCP-Atlas, and +6% on conversational benchmarks including $2$-Bench and VitaBench.
  arXiv  Detail & Related papers  (2026-05-18T17:37:40Z)
• Orchard: An Open-Source Agentic Modeling Framework [124.68499958175111]
  We present Orchard, an open-source framework for scalable agentic modeling.<n>At its core is Orchard Env, a lightweight environment service providing reusable primitives for sandbox lifecycle management.<n>On top of Orchard Env, we build three agentic modeling recipes.
  arXiv  Detail & Related papers  (2026-05-14T16:35:12Z)
• ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation [55.947962672433675]
  ChipMATE is the first self-trained multi-agent framework for RTL generation.<n>Inspired by industrial practice, ChipMATE pairs a Verilog agent with a Python reference-model agent that mutually verify each other's outputs.<n>ChipMATE achieves 75.0% and 80.1% pass@1 on VerilogEval V2 with 4B and 9B base models.
  arXiv  Detail & Related papers  (2026-05-13T01:04:21Z)
• ClawGym: A Scalable Framework for Building Effective Claw Agents [47.47444724291439]
  We present ClawGym, a scalable framework that supports the full lifecycle of Claw-style personal agent development.<n>ClawGym-SynData is a dataset of 13.5K filtered tasks synthesized from persona-driven intents and skill-grounded operations.<n>We then train a family of capable Claw-style models, termed ClawGym-Agents, through supervised fine-tuning on black-box rollout trajectories.<n>We further construct ClawGym-Bench, a benchmark of 200 instances through automated filtering and human-LLM review.
  arXiv  Detail & Related papers  (2026-04-29T17:12:22Z)
• KAT-Coder-V2 Technical Report [45.53423367042574]
  We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou.<n>KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains.<n>We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances.
  arXiv  Detail & Related papers  (2026-03-29T14:01:35Z)
• SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding [41.98672557723593]
  We introduce SWEQA-Pro, a benchmark constructed from diverse, long-tail repositories with executable environments.<n>We also propose a scalable synthetic data pipeline that powers a two-stage training recipe: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning from AI Feedback (RLAIF)<n> Empirically, a Qwen3-8B model trained with our recipe surpasses GPT-4o by 2.3 points on SWE-QA-Pro and substantially narrows the gap to state-of-the-art models.
  arXiv  Detail & Related papers  (2026-03-17T05:12:48Z)
• 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)
• Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem [90.17610617854247]
  We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimize the production pipeline for agentic model.<n>ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering.<n>We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories.
  arXiv  Detail & Related papers  (2025-12-31T14:03:39Z)
• State-of-the-art Small Language Coder Model: Mify-Coder [4.57001984042699]
  Mify-Coder achieves comparable accuracy and safety while significantly outperforming much larger baseline models on standard coding and function-calling benchmarks.<n>Our training pipeline combines high-quality curated sources with synthetic data generated through agentically designed prompts.<n> Quantized variants of Mify-Coder enable deployment on standard desktop environments without requiring specialized hardware.
  arXiv  Detail & Related papers  (2025-12-26T18:16:02Z)

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.