9 papers
Understanding Knowledge Distillation in Post-Training: When It Helps and When It Fails
Xin Liu, Simin Ma, Shujian Liu +5
Large language models (LLMs) achieve strong performance across many tasks, but their high computational cost limits deployment in resource-constrained environments. Knowledge Disti…
PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration
Shuyu Zhang, Yaqi Shi, Lu Wang
LLM multi-agent systems often coordinate through natural-language dialogue or loosely structured shared memory, making intermediate state difficult to validate, attribute, and audi…
EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter Adaptation
Shuyu Zhang, Lingfeng Pan, Qicheng Wang +6
Speculative decoding accelerates Large Language Model inference through draft-then-verify generation, yet lightweight draft models face coupled efficiency and quality limitations:…
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
Muhammad Khalifa, Zohaib Khan, Omer Tafveez +2
Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence rem…
Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation
Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim +6
Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories inclu…
Process Reward Models That Think
Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran +5
Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling. PRMs require step-level supervision, making them expensive to tr…