5 papers · 2 filters
AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs
Sheng Liang, Yongyue Zhang, Nathanael Brian +4
Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool use, and multi-turn interactions. To control latency, deployments routinely comp…
AI Learning and Conceptual Transfer in the Game of Hidden Rules
Christo Mathew, Wentian Wang, Jacob Feldman +4
This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules from trial-and-error feedback,…
ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis
Hao Wang, Jindong Han, Wei Fan +1
Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created sign…
When More Thinking Hurts: Overthinking in LLM Test-Time Compute Scaling
Shu Zhou, Rui Ling, Junan Chen +3
Scaling test-time compute through extended chains of thought has become a dominant paradigm for improving large language model reasoning. However, existing research implicitly assu…
Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration
Hang Lv, Hongchao Gu, Ruiqing Yang +5
Generative listwise reranking leverages global context for superior retrieval but is plagued by intrinsic position bias, where models exhibit structural sensitivity to input order…