13 papers
Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
Guangyue Peng, Zongchao Chen, Wen Luo +9
Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but answer-visible generation can justify a pre-committed answer rather than derive…
Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts
Chen Yang, Guangyue Peng, Jiaying Zhu +12
We present Nanbeige4.1-3B, a unified generalist language model that simultaneously achieves strong agentic behavior, code generation, and general reasoning with only 3B parameters.…
Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts
Riyang Bao, Cheng Yang, Dazhou Yu +3
Geospatial reasoning is essential for real-world applications such as urban analytics, transportation planning, and disaster response. However, existing LLM-based agents often fail…
Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
Chengyuan Yang, Zequn Sun, Wei Wei +1
Memory management is vital for LLM agents to handle long-term interaction and personalization. Most research focuses on how to organize and use memory summary, but often overlooks…
Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations
Chengxu Yang, Jingling Yuan, Siqi Cai +2
Hallucinations in large language models (LLMs) are commonly regarded as errors to be minimized. However, recent perspectives suggest that some hallucinations may encode creative or…
Automating High Energy Physics Data Analysis with LLM-Powered Agents
Eli Gendreau-Distler, Joshua Ho, Dongwon Kim +3
We present a proof-of-principle study demonstrating the use of large language model (LLM) agents to automate a representative high energy physics (HEP) analysis. Using the Higgs bo…