arXiv:2608.29675v1 Announce Type: cross Abstract: Repository exploration is a distinct and costly stage of coding-agent pipelines: before generating a patch, an agent must identify which repository f...
BoostAPR is a three-stage framework that improves automated program repair by using execution-grounded reinforcement learning with dual reward models. The approach first fine‑tunes a model on execution‑verified demonstrations, then trains a sequence‑level assessor and a line‑level credit allocator from execution outcomes, and finally applies PPO optimization where the line‑level model redistributes rewards to critical edit regions. Evaluated on SWE‑Gym and four benchmarks, BoostAPR achieves significant gains, including 40.7% on SWE‑bench Verified and 95.0% on QuixBugs, demonstrating strong cross‑language generalization.
arXiv:2608.27906v2 Announce Type: replace Abstract: Interactive web application generation requires models to produce usable HTML, CSS, and JavaScript applications from natural language requests. Unl...
arXiv:2609.22068v1 Announce Type: new Abstract: Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich sourc...
LEGO-RL is a framework that connects native coding-agent harnesses with scalable policy‑gradient training without altering the harnesses’ internal flow. It achieves faithful optimization through in‑process LLM proxying, reliable execution via sandbox orchestration, and observable training with automated validation and a Live UI. Experiments show LEGO‑RL improves the Qwen3.5‑35B‑A3B model’s performance on three native harnesses while preserving high rollout‑training probability correlation.
arXiv:2607. 08837v1 Announce Type: cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers.
StraTA introduces Strategic Trajectory Abstraction, a framework that samples a compact strategy from the initial task state and conditions subsequent actions on that strategy, training strategy generation and action execution jointly with a hierarchical GRPO-style rollout design. The method enhances exploration and credit assignment over long horizons by incorporating diverse strategy rollouts and critical self-judgment. Experiments on ALFWorld, WebShop, and SciWorld demonstrate that StraTA consistently improves sample efficiency and final performance, achieving success rates of 93.1% on ALFWorld, 84.2% on WebShop, and a 63.5% overall score on SciWorld, surpassing frontier closed‑source models.
arXiv:2607. 05471v1 Announce Type: cross Abstract: We present KAT-Coder-V2.
The paper introduces Potential-Guided Policy Optimization (PGPO), a method for multi-turn agentic tasks that improves credit assignment by estimating empirical state potentials from anchor-state-group return statistics. PGPO derives action advantages from potential differences between adjacent states, enabling cross-trajectory credit propagation and finer-grained step-level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop demonstrate strong performance compared to recent group-based reinforcement learning methods, with negligible training overhead.
The paper introduces GRAFT, a Graph-based Faithful sTep-level credit-assignment framework that constructs a trajectory graph from rollout trajectories, recovers node state-values via Bellman iteration, and assigns step-level advantages based on node value differences. It also proposes Graph GAE to further reduce state-value estimation bias. Experiments on multi-turn agentic benchmarks demonstrate consistent improvements over GRPO and other recent agentic RL algorithms.
arXiv:2608. 07147v1 Announce Type: new Abstract: Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from compilation and tests provides objective verification.
arXiv:2607. 13988v1 Announce Type: new Abstract: Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training.