Showing 2026Show all
3 papers · 1 filter
cs.AI2026
Agentic Multi-Turn Reasoning: A Fairness Approach
Thanh-Dat Truong, Sankalp Pandey, Hugh Churchill +3
Recent advances in Large Language Models (LLMs) have enabled agentic systems capable of solving complex tasks through multi-turn planning, tool use, verification, and memory update…
cs.CV2026
Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models
Sultan Alshehri, Zhantao Yang, Han Zhang +1
Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries like "umbrella and no person"…
cs.AI2026
PACE: Policy-Native Adaptive Decision Timing for Long-Horizon Reasoning
Chen Li, Zhantao Yang, Fangyi Chen +3
Long-horizon reasoning requires deciding not only what actions to take, but how many to execute open-loop before replanning. This number, the execution depth, balances replanning c…