The paper evaluates additive activation steering in chat and agent contexts, showing that the commonly used gain ratio (Δ_agent/Δ_chat) fails to reliably indicate potency and efficacy across multiple models and dose-response cells. By replacing the gain with a location metric, dEC50 (difference in EC50 between agent and chat), the authors demonstrate a more robust, two‑sided measure that consistently captures cross‑context shifts. The study also reports several refuted and unanswered claims, emphasizing that a single operating point cannot distinguish between displacement and gain effects.
By Lucas Pinto
The paper reports that agent evaluations often show a tool‑call rate of zero even when the model emits valid calls, because the interface censors the trajectory before downstream components see it. Experiments on BFCL v4 and tau‑bench demonstrate that swapping the serving adapter can change the observed call rate from 0.00 to 0.96/0.19 or from 0 to 636 calls, indicating that the interface—not the model—causes the discrepancy. A 98‑line preflight check is released to detect such silent failures, highlighting that tool‑call rates depend on the model‑interface stack rather than the model alone.
By Wenbo Wang
The study investigates which components of a neural network contribute to rapid generalization (grokking) and how stable that improvement remains during further training. By transferring internal attention and MLP weights along with token embeddings and readout, the authors achieve a 5.46‑percentage‑point boost in early accuracy and a 558‑step reduction in confirmation latency, while also demonstrating that freezing transferred representations largely prevents post‑grokking relapse. The work delineates clear component‑level differences between acceleration and stability, and identifies architectural limits where omitting donor embeddings leads to significant performance loss.
By Zeyu Jia
arXiv:2607. 04510v1 Announce Type: cross Abstract: Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.
By Lyndon Drake (University of Oxford), Zandi Eberstadt (University of Oxford)
The paper introduces a schema‑adaptive action‑conditioned Joint‑Embedding Predictive Architecture (SAAC‑JEPA) for cross‑machine CNC transfer when only a subset of sensors overlap between source and target machines. Experiments show that pretraining does not improve source‑only forecasting, but a carefully selected action‑conditioned JEPA model achieves a zero‑shot RMSE of 0.546 on the target, outperforming persistence but falling short of certain baseline models. Ablation studies reveal that adding RevIN improves RMSE but harms calibration, and limited post‑lock adaptation can further reduce error.
By Ayoub Louaye Bouaziz, Matthieu Ostertag, Anton Demasles
arXiv:2607. 27849v1 Announce Type: cross Abstract: An open-weight LLM can write composition setpoints every five minutes.
By Christian Rosenthal
arXiv:2608. 11212v1 Announce Type: new Abstract: Top-k Mixture-of-Experts (MoE) routing is discontinuous, so a deployment-motivated numerical disturbance -- simulated 4-bit KV-cache quantization read by a protected BF16 gate -- pushes tokens across decision boundaries and flips which experts fire.
By Parvel Gu
arXiv:2607. 24339v1 Announce Type: new Abstract: Large language model (LLM) agents inherit reactive failure modes: escalation under provocation, sycophantic drift under flattery, perseveration when stuck.
By Dushyant Sharma
arXiv:2606. 12923v2 Announce Type: replace-cross Abstract: AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects.
By Gareth Seneque, Lap-Hang Ho, Nafise Erfanian Saeedi, Jeffrey Molendijk, Tim Elson
arXiv:2606. 12923v1 Announce Type: cross Abstract: AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects.
By Gareth Seneque, Lap-Hang Ho, Nafise Erfanian Saeedi, Jeffrey Molendijk, Tim Elson
The paper investigates whether modifying a model’s internal activations—through activation steering—actually changes the computational state used in subsequent processing or merely biases the computation toward a desired output. In a controlled state‑tracking task, editing a trace‑supervised register causes the model to apply the next operation to the edited state, confirming that the edit changes the state. However, in two large‑language‑model settings (Qwen and Llama), mean activation steering does not replicate the natural internal configuration used during task execution; steering vectors are far larger than typical natural changes and achieve only a fraction of the effect of full‑layer patching. Thus, a successful steering intervention does not necessarily reproduce the natural target activation at the intervention layer, and should be interpreted as a state change only when later computation actually uses the edited value in the intended semantic way.
By Benjamin Shih, John Winnicki, Eric Darve
arXiv:2608. 15809v1 Announce Type: new Abstract: Behavioral accuracy, linear decodability, and successful activation interventions do not by themselves show that a model carries an operation-level structure from one symbolic domain to another.
By Xinyi Shan