Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable. Existing methods for shaping how a model reasons are prompt based approaches and operate at the input level, offering no fine-grained control over the reasoning process itself. Related work analyzes and discovers latent transition dynamics in the reasoning traces from Large Language Models. Building on this, we statistically characterize these states, and show that failure trajectories get stuck in self-loops, exhausting the token budget wit
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 87%lllyasviel/ControlNet →
“Fuzzy title match (0.94): “Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning ” ≈ “lllyasviel/ControlNet””
- FuzzySimilar title/name (fuzzy) · 87%lllyasviel/ControlNet-v1-1 →
“Fuzzy title match (0.94): “Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning ” ≈ “lllyasviel/ControlNet-v1-1””
- PossiblePossibly related (embedding) · 55%IEEE Rolls Out Large Language Models Virtual Training Course →
- FuzzyOverlapping authors or contributors · 62%affaan-m/ECC →
“Shared author/contributor keys: jiang”
- FuzzyOverlapping authors or contributors · 62%BerriAI/litellm →
“Shared author/contributor keys: jiang”
- FuzzySimilar title/name (fuzzy) · 59%builderz-labs/mission-control →
“Fuzzy title match (0.73): “Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning ” ≈ “builderz-labs/mission-control””
- LinkedLinked via arxiv author · 85%Sheldon Yu →
“Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering”
- LinkedLinked via arxiv author · 85%Tong Yu →
“Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering”