Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving
Xin Cheng, Junming Yang, Ning Xu
Puzzles offer a natural testbed for Large Language Models (LLMs) reasoning because they pose verifiable goals under partial information and require multi-step decisions to reach a…
cs.CL2026
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Tong Zheng, Xidong Wu, Zheng Zhang +14
Recursive self-improvement is becoming essential for autonomous AI agents, whose progress depends on discovering high-value solutions across complex domains. Effective exploration…