6 papers · 1 filter
Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
Monishwaran Maheswaran, Leon Lakhani, Zhongzhu Zhou +16
We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates collapse toward narrow modes, whi…
: Faster Test-Time Scaling through Speculative Drafts
Mert Cemri, Nived Rajaraman, Rishabh Tiwari +6
Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thor…
Agentic Test-Time Scaling for WebAgents
Nicholas Lee, Lutfi Eren Erdogan, Chris Joseph John +4
Test-time scaling has become a standard way to improve performance and boost reliability of neural network models. However, its behavior on agentic, multi-step tasks remains less w…
Why Do Multi-Agent LLM Systems Fail?
Mert Cemri, Melissa Z. Pan, Shuyi Yang +10
Despite enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains on popular benchmarks are often minimal. This gap highlights a critical need for a principled understa…
Learning Adaptive Parallel Reasoning with Language Models
Jiayi Pan, Xiuyu Li, Long Lian +6
Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chai…
K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences
Zhikai Li, Xuewen Liu, Dongrong Joe Fu +4
The rapid advancement of visual generative models necessitates efficient and reliable evaluation methods. Arena platform, which gathers user votes on model comparisons, can rank mo…