collaborators

5 papers

cs.AI2026

SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization

Yuncheng Hua, Sion Weatherhead, Mehdi Jafari +2

Automated simulator construction requires distributional fidelity, distinguishing it from generic code generation. We identify two failure modes in long-horizon LLM agents: context…

cs.CL2026

Mechanistic Indicators of Steering Effectiveness in Large Language Models

Mehdi Jafari, Hao Xue, Flora Salim

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread u…

cs.CL2026

Is my model "mind blurting"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)

Quoc Tuan Pham, Mehdi Jafari, Flora Salim

Test-time compute is central to large reasoning models, yet analysing their reasoning behaviour through generated text is increasingly impractical and unreliable. Response length i…

cs.AI2025

SOCIA-: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation

Yuncheng Hua, Sion Weatherhead, Mehdi Jafari +2

In this paper, we present SOCIA-, an end-to-end, agentic framework that treats simulator construction asinstance optimization over code within a textual computation graph.…

cs.AI2025

SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation

Yuncheng Hua, Sion Weatherhead, Mehdi Jafari +2

In this paper, we present SOCIA-Nabla, an end-to-end, agentic framework that treats simulator construction asinstance optimization over code within a textual computation graph. Spe…