Agent decision models select actions in a single forward pass from inputs that combine environmental observations with the agent's own record of previous actions. When an action fails silently, these sources can conflict: the record reports success, but the environment shows that the step did not take effect. We ask wh...
Tina Khezresmaeilzadeh, Seyedarmin Azizi, Erfan Baghaei Potraghloo et al.· 0 citations
Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for behavioral control. The standard construction, contrastive activation addition (CAA), is fragile, as on many inputs it shifts behavior in the wrong direction. To explain...
Seyedarmin Azizi, Arya Fayyazi, Parsa Razmara et al.· 0 citations
A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text. Recent work places these models in agent systems as guardrails: the component that reads a proposed tool call or incoming message and decides whether to allow it....
Seyedarmin Azizi, Erfan Baghaei Potraghloo, M. Pedram· 1 citation
A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the incorrect answers together hold more probability. The power distribution raises each complete answer's probability to a power above one and renormalizes, shifting probabili...
A typed decision model answers a fixed question about an input by returning a probability for each of several caller-defined options. Each option carries a short label and a written definition, which is where a developer states the rule the model should apply. Jev introduced this interface for routing, moderation and t...
Seyedarmin Azizi, Erfan Baghaei Potraghloo, M. Pedram· 1 citation
Chopthin-Consensus Power Sampling (CCPS) is introduced, demonstrating that diversity-preserving resampling and diversity-aware selection are complementary mechanisms for training-free LLM reasoning.
CircuitSteer is introduced, a novel framework that leverages Sparse Autoencoders (SAEs) to identify and manipulate coherent semantic circuits distributed across multiple layers that yields strictly more robust and effective behavioral control than static single-point interventions.
Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
