SWE-1.7: Frontier Intelligence at a Fraction of the Cost

Today, we’re launching SWE-1.7, the most capable model we’ve trained so far. It reaches frontier-level intelligence at a much lower cost, advancing the cost-performance Pareto curve.

SWE-1.7 is the result of broad improvements across our RL pipeline: better infrastructure, more stable training, higher-quality data, and new techniques for long-horizon tasks. Since SWE-1.7 was trained from a Kimi K2.7 base, which had already undergone extensive RL post-training, the large additional gains from our own training challenge the idea of a ‘post-training ceiling’ and suggest that RL can push capabilities much further than previously believed.

At Cognition, we have been formulating and refining principles for good agentic software engineering both in evaluation, with FrontierCode^1,2, and now in training, with SWE-1.7. Our model is particularly optimized for longer-horizon asynchronous tasks, an important component of high-quality software engineering.

SWE-1.7 is available today in Devin (Web, Desktop, and CLI) via Cerebras at 1000 TPS. We encourage you to try it for yourself!

The rest of this post covers how we trained SWE-1.7: the infrastructure, algorithms, and data work behind our model. We cover four important components that stand out.

• Preserving entropy and stabilizing training: Long RL runs face two challenging problems: entropy collapse, and instability due to numerical drift between training and inference. We hunted down and addressed causes of each, which enabled training to keep improving well past where earlier runs stalled.
• Multi-cluster training and fault tolerance: RL doesn’t need all of its inference compute in one cluster. We trained on clusters across three continents, shipped weight updates through object storage, and built fault tolerance so that hardware failures never stalled the run.
• Curating high-quality data: We built an extensive data-quality pipeline that runs each task through automated execution tests, filters out tasks with low learning signal, and hardens tasks to prevent reward-hacking.
• Self-compaction for long-horizon tasks: The model learns to summarize its working state and resume from the summary, extending task horizons past the raw context window. We use an alternating length penalty to incentivize concise output without sacrificing correctness.

Finally, we conclude by sharing some observations on interesting behavioral tendencies, such as careful exploration and concise reasoning, that the model acquired as a result of our training setup.

Preserving Entropy and Stabilizing Training#

We found training stability to be a key contributor to predictable improvement at scale.

When training with asynchronous RL³, one of the most problematic issues we encountered was the KL divergence mismatch between inference and training⁴, since the trainer policy is usually different from the sampling policy. In the past, to correct for this (albeit at smaller scale), we used importance-sampling⁵ and quantization-aware training for low-precision rollouts in NVFP4 + experts routing replay^6,7.

Here we present additional interventions that become more important at larger scale.

We find that top-p sampling⁸ contributes significantly to staving off entropy collapse^9,10, where a strong model stops exploring and reward plateaus within a few hundred steps.

Very low probability tokens are often part of trajectories that have gone off track or out of distribution. These trajectories are likely to produce low reward, and properties of the softmax function lead to these tokens sharpening the token probability distribution. Indeed, suppose we have three tokens with logits $x_1>x_2\gg x_3$ and probabilities $p_i = \frac{e^{x_i}}{e^{x_1} + e^{x_2} + e^{x_3}}$, where token 3 is a low probability token that leads to low reward. If we sample token 3, the gradient of its logprob with respect to the logits $x_1, x_2, x_3$ is:

and the policy gradient update to the logits is $\Delta x_i \propto \hat{A}\ \nabla \log p_3$, where $\hat{A}$ is the advantage of the sampled token. Since this trajectory earns low reward, $\hat{A} < 0$ and the updates are

In these updates, $x_3$ is penalized, and $x_1$ grows more than $x_2$. Sampling $x_3$ therefore widens the lead of the already-dominant token, sharpening the distribution and decreasing entropy. Top-$p$ sampling prevents these low probability tokens from being sampled and used as optimization targets in the first place!

Policy entropy across training

This entropy-preservation effect makes top-$p$ sampling desirable in our rollouts. But naively implementing top-$p$ clearly increases the training-inference mismatch — the trainer computes probabilities as a selection from all tokens, while rollouts sample from the top-$p$ subset, so the distributions have higher divergence, leading to collapse after a small number of steps. Thus, we implement sampling distribution replay¹¹, where we record a kept-set of tokens available for sampling at rollout time, and renormalize probabilities with those masks in the trainer. With this fix, our run’s entropy stays roughly constant over the course of training and inference-training divergence stays bounded.

Training-inference mismatch across training

Another interesting result of using top-p sampling replay is a targeting of only tokens with $p < \text{top\_p\_threshold}$. Tokens with probability above the threshold have a keepset of size 1, so their renormalized probability distribution is a constant 1, and gradients are zeroed out. We found empirically that a large fraction of the tokens sampled by the model are above standard top-p thresholds, so they are excluded from the overall gradient computation. This reduces gradient noise and lets the optimization algorithm focus on the high-learning signal tokens in the trajectory.

We also find benefits from using the Muon optimizer¹² and eliminating non-deterministic operations in the trainer.

Multi-cluster Training#