Can Editing 1 Neuron Fix Repetition Loops in LLMs?

Yes. Can it cure doom loops? Probably not. The Gemma 4 instruction-tuned models share a reproducible failure: on long factual enumeration prompts, such as listing every episode of a TV series, the 88 IAU constellations, or the 151 original Pokemon, they collapse into repetition, either a tight verbatim loop or a list whose entries decay onto a single answer. These loops occur at rates as high as 95% and survive prompt rewording, inference-engine changes, and most sampling adjustments. In this paper we explore whether this behavior is localized enough to remove by weight edits. To localize the cause, we use per-layer ablation and per-neuron attribution, then confirm the strongest candidates with full-generation sweeps. The loops trace to a small set of MLP neurons (or, in the 26B-A4B Mixture-of-Experts model, a few routed experts) which we suppress with static weight edits. These "surgeries" can be as small as a single sign-inverted neuron (in the E2B model). The size of the effective edits grows with model scale, but in all cases, the loop patterns can be addressed at normal generation budgets while preserving general-purpose benchmark scores. However, the edits do not solve everything: we also study longer thinking budgets, where the two larger models most visibly enter doom looping, i.e. a non-convergent regime in which the model self-corrects in circles over a fact it cannot recall, exhausting the budget without committing to a final answer. We show this residual failure is reduced but not eliminated by the same edits, and argue it is fundamentally a knowledge-precision problem rather than a removable circuit; weight surgery can delete a loop, but it cannot supply a missing fact. Our results are both a feasibility demonstration, that is, evidence that a concrete generation pathology can be localized to a few parameters and edited out, and a delineation of where that approach stops.

EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation

On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without introducing model distribution drift, and consequently, regression in general tasks. On-Policy Self-Distillation (OPSD) is an efficient use-case of OPD, which is appealing as it requires only a single model as a student and teacher, and it also has the benefit of providing privileged context that is a absent at inference time (e.g. a persona, a private fact, or a worked solution) to the teacher during the training process. The challenge in this approach is that the privileged information can change model behavior more than intended: it can modify reasoning, degrade general capabilities, and affect performance indicators like response length, style, or local token preferences. Consequently, OPSD may train the student on side effects rather than a desired, transferable behavior. In this paper, we study this problem in a rare-token/identity setting and propose EviDence GuidEd On-Policy Distillation (EDGE-OPD), a modification of OPSD with two distinct characteristics: a) it uses guided rollouts to inject privileged-context behavior to the student at sampling time, so that the rare target behavior is actually present in the on-policy data, and b) it applies an evidence mask: the student is updated only at token positions where the privileged context supports the sampled token, rather than on every token in the rollout. We empirically show that OPSD (and its variant RLSD, with and without a verifier) completely fail to learn a target identity, while the integration of guided rollouts allows them to succeed. Additionally, mask-region ablations show that the persona signal is localized to the positive-evidence tail, allows us to draw valuable insights about efficient knowledge transfer and preservation of general purpose capabilities.

EdgeRunner 20B: Military Task Parity with GPT-5 while Running on the Edge

We present EdgeRunner 20B, a fine-tuned version of gpt-oss-20b optimized for military tasks. EdgeRunner 20B was trained on 1.6M high-quality records curated from military documentation and websites. We also present four new tests sets: (a) combat arms, (b) combat medic, (c) cyber operations, and (d) mil-bench-5k (general military knowledge). On these military test sets, EdgeRunner 20B matches or exceeds GPT-5 task performance with 95%+ statistical significance, except for the high reasoning setting on the combat medic test set and the low reasoning setting on the mil-bench-5k test set. Versus gpt-oss-20b, there is no statistically-significant regression on general-purpose benchmarks like ARC-C, GPQA Diamond, GSM8k, IFEval, MMLU Pro, or TruthfulQA, except for GSM8k in the low reasoning setting. We also present analyses on hyperparameter settings, cost, and throughput. These findings show that small, locally-hosted models are ideal solutions for data-sensitive operations such as in the military domain, allowing for deployment in air-gapped edge devices.

A Hybrid Approach for Reinforcement Learning Using Virtual Policy Gradient for Balancing an Inverted Pendulum

Using the policy gradient algorithm, we train a single-hidden-layer neural network to balance a physically accurate simulation of a single inverted pendulum. The trained weights and biases can then be transferred to a physical agent, where they are robust enough to to balance a real inverted pendulum. This hybrid approach of training a simulation allows thousands of trial runs to be completed orders of magnitude faster than would be possible in the real world, resulting in greatly reduced training time and more iterations, producing a more robust model. When compared with existing reinforcement learning methods, the resulting control is smoother, learned faster, and able to withstand forced disturbances.

Recommending More Efficient Workflows to Software Developers

Existing recommendation systems can help developers improve their software development abilities by recommending new programming tools, such as a refactoring tool or a program navigation tool. However, simply recommending tools in isolation may not, in and of itself, allow developers to successfully complete their tasks. In this paper, I introduce a new recommendation system that recommends workflows, or sequences of tools, to developers. By learning more efficient workflows, the system could make software developers more efficient.