Tree-Ising: Repairing Language Models with Bit-Level Ising Edits
Tree-Ising: Repairing Language Models with Bit-Level Ising Edits
Tree-Ising fixes the inference loop of large language models by solving sparse Ising/QUBO problems on BF16 parameters, improving mathematical benchmark accuracy with fewer weight edits without gradient or LLM-token costs.
Published on Nov 10
Authors:
Abstract
Tree-Ising repairs reasoning loops in LLM weights by solving sparse Ising/QUBO problems over BF16 parameters, improving math benchmark accuracy with fewer weight edits and no gradient or LLM-token cost.
Weight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their GPT-6 Astra agent corrected the reasoning loops of Qwen3.5-0.8B without gradients, using 158 agent turns, 89.7 million tokens, and 50 forward-pass requests. Our method, Tree-Ising, casts this repair as a sparse discrete optimization problem over the model's own BF16 weights. Forward statistics define an objective that weakens a loop direction, strengthens a concluding direction, and preserves the layer's output on productive tokens. Within a state-tree representation, where lossless BF16 storage acts as a special case, the admissible edits are sign flips and exponent shifts that preserve all shared group exponents and mantissas. We decompose this objective exactly into independent QUBO (Ising) problems, one per output row, which we solve on a GPU using simulated annealing or quantum-inspired simulated bifurcation. On the agent's two layers, Tree-Ising achieves 54.6% on MATH-500, outperforming the agent's edit (51.7%) under the same evaluation protocol, while the base model scores 7.9% as reported. The simulated bifurcation solver yields a statistically indistinguishable repair at 55.1%. Both solvers outperform the agent edit across all five math benchmarks, with statistically significant improvements on MATH-500 and GSM8K after correcting for multiple comparisons. Our approach modifies 13% to 17% fewer weights and reduces BF16 bit flips by a factor of 2.2 to 2.3. It requires only four forward-pass requests and zero LLM tokens, with the annealing recipe costing about $0.90 in GPU time. On Qwen3.5-2B, with layers and dose selected using only the base model, the same recipe increases greedy GSM8K accuracy from 21.6% to 69.4%. As a proof of concept, we execute an eight-variable repair subproblem using QAOA on an IBM Heron processor.
View arXiv page View PDF GitHub 0 Add to collection
Get this paper in your agent:
hf papers read 2611.14210
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.14210 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.14210 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.14210 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Source: Hugging Face Daily Papers · huggingface.co