collaborators

24 papers

cs.CL2026

Learning When to Attend: Conditional Memory Access for Long-Context LLMs

Sakshi Choudhary, Aditya Chattopadhyay, Luca Zancato +4

Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is…

cs.SE2026

StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns

Vlad Sobal, Shuo Yang, Yuting Zhang +2

We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike t…

cs.LG2026

Reinforcement-aware Knowledge Distillation for LLM Reasoning

Zhaoyang Zhang, Shuli Jiang, Yantao Shen +6

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such model…

cs.CL2026

DLLG: Dynamic Logit-Level Gating of LLM Experts

Bingnan Li, Zhaoyang Zhang, Xiaoze Liu +6

Leveraging multiple specialized LLMs can combine complementary strengths, but existing approaches trade adaptability for stability: routing commits prematurely, heuristic ensemblin…

cs.LG2026

EvoMAS: Evolutionary Generation of Multi-Agent Systems

Yuntong Hu, Yuting Zhang, Matthew Trager +4

Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but designing effective MAS architectures…

cs.LG2026

Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression

Liangzu Peng, Aditya Chattopadhyay, Luca Zancato +3

Linear State-Space Models (SSMs) offer an efficient alternative to softmax Attention with constant memory and linear compute, but their lossy, fading summary of the past hurts reca…