2 papers
cs.CL2026
Understanding Target Probability Reuse in Speculative Decoding
Jungseob Lee, Giyoon Jang, Chailin Nam +6
Speculative decoding uses a target model to verify a tree of draft tokens in parallel. We study whether the resulting next-token distributions can help select the next tree. For un…
cs.CL2026
Structured but Silent: Probing Capability Requirements in LLM Hidden States
Kyojun Choo, Minsoo Song, Yunju Kang +1
Reliable tool use requires more than triggering a mechanism or matching a query to an API description. Before selecting a specific tool, an agent must first infer the capability re…