collaborators

10 papers

cs.AI2026

StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems

Yanwen Peng, Delvin Ce Zhang, Xi Wang +1

Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the sender's con…

cs.CL2026

Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility

Jo-Ku Cheng, Nikolaos Aletras, Marco Valentino

Pre-pretraining language models (LMs) on symbolic data can accelerate and improve natural language acquisition. However, existing pre-pretraining tasks, such as Dyck and procedural…

cs.LG2026

On Effectiveness and Efficiency of Agentic Tool-calling and RL Training

Tong Liu, Cheng Qian, Matej Cief +4

Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge. This paper studies tool-calling along…

cs.CL2026

Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models

Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter +3

Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (Co…

cs.CL2026

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models

Danae Sánchez Villegas, Danae Sánchez Villegas, Samuel Lewis-Lim +2

Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear. We analyze reasoni…

cs.CR2026

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing

Anthony Hughes, Vasisht Duddu, N. Asokan +2

Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms su…