arXiv:2605. 26343v2 Announce Type: replace Abstract: Mechanistic interpretability seeks to explain a model's behaviour by finding its circuit: the sparse subgraph of the model's computation that is causally responsible for it.
arXiv:2607. 18921v1 Announce Type: cross Abstract: Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior.
arXiv:2605. 28860v2 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) frequently induces catastrophic forgetting of prior capabilities.
arXiv:2608. 08536v1 Announce Type: new Abstract: Circuit localization is a mechanistic interpretability task whose goal is to identify a sparse subgraph of a transformer's computation graph sufficient to reproduce a particular behavior.
arXiv:2606. 12386v1 Announce Type: cross Abstract: Advancing scientific understanding through mechanistic modeling requires posing the right experimental questions to yield maximally informative data.
arXiv:2606. 25394v1 Announce Type: new Abstract: Finding minimal arithmetic circuits for polynomials over finite fields is a combinatorially hard problem central to algebraic complexity theory.
arXiv:2607. 23263v1 Announce Type: new Abstract: Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them with reinforcement learning.
arXiv:2606. 24026v1 Announce Type: new Abstract: Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult to standardize.
arXiv:2601. 11061v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is highly effective for enhancing LLM reasoning, yet recent evidence shows models like Qwen 2.
arXiv:2601. 09624v2 Announce Type: replace-cross Abstract: Machine unlearning is becoming essential for building trustworthy and compliant language models.
arXiv:2606. 19476v1 Announce Type: cross Abstract: Effective machine learning depends not only on how we model data, but also on what data we choose to collect.
arXiv:2601. 15158v4 Announce Type: replace-cross Abstract: Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought).
arXiv:2607. 06503v1 Announce Type: new Abstract: Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable.