cs.AINov 9, 2026

W-ISA: Transactional Execution of Weight-Space Intervention Programs

Authors: Ekrem Aksoy

Abstract

We present W-ISA, a software instruction set and transactional runtime for executing weight-space intervention programs on pretrained language models. Shape-checked instructions express parameter updates, projections, ablations, and rank-one transformations. The runtime applies these programs within request-scoped execution contexts and restores saved parameters after completion or interruption. Activation-based match-action rules connect measured model states to intervention selection. We evaluate restoration and replay on SmolLM-135M-Instruct and Qwen2.5-1.5B-Instruct, and compare materialized rank-one updates with equivalent PyTorch hooks on the latter. In 45 timed requests, both intervention implementations produce identical greedy sequences at 32, 128, and 512 tokens; their maximum prompt-logit difference is 0.000184. On the complete WikiText-2 raw test split, the combined SmolLM attention-head ablation and MLP projection changes perplexity from 22.2353 to 22.3188, a relative increase of 0.3754%. W-ISA separates intervention specification, execution, and measurement, making parameter-level experiments reproducible and composable.

Figures & tables

Explore similar work

Nov 5, 2026

WeightLoop: Weight-Space Programming with Experimental Feedback

Scientific predictors guide costly experiments, yet returned measurements often reveal errors that matter for subsequent experimental choices. WeightLoop turns this feedback into persistent model updates through a reusable Weight-Space Programming (WSP) editor. We use GPT-6 Astra and DeepSeek to construct update programs from the scientific objective, model computation and editable parameters. These programs use accumulated measurements to estimate parameter corrections, validate them on feedback and save accepted changes in the original model. With identical feedback and writable parameters, four pretrained scientific predictors obtain 5.10-18.56% lower primary error. For weather prediction, changing four output-bias parameters reduces root mean squared error by 13.28%. Functional ranking and sequential discovery further connect reusable editing programs to improved experimental choices.
Nov 13, 2026

WeightBench: Evaluating Language Models as Weight-Space Programmers

Recent work shows that large language models (LLMs) can operate directly on the parameters of other neural networks. They can read what a network was trained to do, fix a network that fails, and write working networks from scratch, all without gradient descent. This capability has been termed Weight-Space Programming (WSP). Exploring this new paradigm systematically requires a robust benchmark. We introduce WEIGHTBENCH, a benchmark that evaluates LLMs of increasing capability on 42 WSP tasks across five tracks: reading, fixing and writing weights, recognizing edits that are impossible, and data-free compression. The networks whose weights the LLMs read and edit range from 2K-parameter control policies to 7B-parameter language models. Experimental benchmark results show that frontier agents can already read small networks and write working control policies without ever running them, but cannot yet patch language models, compress them without data, or tell an impossible edit from a hard one. On all 42 tasks, Claude Opus 5.5 reaches a macro score of 0.535 (Sonnet 5.5 0.466, Haiku 5.5 0.402, DeepSeek v4-flash 0.215); on the 38 tasks it was run on, GPT-6.1-sol reaches 0.568 against Opus's 0.546. Code, the task registry, our OS-level sandbox harness, and the live leaderboard are publicly available at https://github.com/Aayush-Marasini/WeightBench.
Nov 17, 2026

Weight Space Programming for Vision Language Model Repair

In weight-space programming, a language model edits a network's weights directly, without gradients. We ask what a successful repair of this kind relies on. We plant faults in the weights of two vision-language models, SmolVLM-256M and LFM2-VL-450M, and check each edit made by a coding agent against the original weights. Without being told where to look, the agent finds rescaled rows in the projector and noise in the vision encoder of both models, infers the unknown scale factors, restores most or all of the rescaled weights to their exact original values, and returns accuracy to near its original level; programs that it writes from such weights repair unseen checkpoints of the same model without feedback. These repairs depend on a trace of how the faults were computed. The original weights have 16-bit precision, and faults computed in 32-bit arithmetic leave low bits that only the damaged weights carry. Rounding those bits away leaves each model's answers to our test questions unchanged, and the agent, unaided, then restores no weight exactly: on SmolVLM it no longer finds the damage, and in a single session on LFM2-VL its only gain comes from rescaling answer-token embeddings, which changes how often the model answers yes. Marking the damaged weights again in their low bits brings the edits back to them. Rounded weights still hold statistical evidence of the rescaling, in the distribution of stored values and in row norms, and one sentence in the prompt that names such a statistic directs the agent's edits to the damaged rows on both models. Swapped rows or columns, which leave the set of stored values unchanged, are not found unaided on either model within our session budgets. We recommend that studies of weight repair report the number format of the weights and include a rounded control.