activity
20242026
collaborators

32 papers

cs.AI2026

LLM-as-a-Verifier: A General-Purpose Verification Framework

Jacky Kwok, Shulu Li, Pranav Atreya +6

Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the abi…

cs.AI2026

TRACE: Capability-Targeted Agentic Training

Hangoo Kang, Tarun Suresh, Jon Saad-Falcon +1

Models often fail to complete agentic tasks because they lack core capabilities required by the target environment. However, mainstream approaches for addressing these failures typ…

cs.CL2026

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

Shayan Talaei, Abhinav Chinta, Devvrit Khatri +3

Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale. Such preferential biases can be intro…

cs.LG2026

KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?

Yunxiang Zhang, Ping Yu, Jianyu Wang +5

Recent large language models (LLMs) can generate custom CUDA kernels that appear to outperform PyTorch on benchmarks such as KernelBench. Building upon this foundational framework,…

cs.CL2026

PolyAlign: Conditional Human-Distribution Alignment

L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2

Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…

cs.MA2026

Decentralized Multi-Agent Systems with Shared Context

Yuzhen Mao, Azalia Mirhoseini

Multi-agent systems (MAS) can scale large language model reasoning at test time by decomposing complex problems into parallel subtasks. However, most existing MAS rely on centraliz…