arXiv:2606. 28365v1 Announce Type: cross Abstract: RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.
By Adnan Qidwai, Anand Eswaran, Sonam Mishra, Jaydeep Sen, Sachindra Joshi
arXiv:2609.24002v1 Announce Type: new
Abstract: Large language model agents increasingly answer financial questions by searching regulatory filings. Such questions are often deceptively under-specifi...
By Xinyu Wang, Tung Sum Thomas Kwok, Zhenghan Tai, Guang Cheng
When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compares final answers and discards the actions.
The study evaluates multi‑agent debate (MAD) in small language models, testing whether cognitive diversity—via personas, sampling temperature, or model identity—drives performance gains. Across 23 models, five tasks, and over 5,500 runs, MAD consistently outperforms single‑model inference but, when matched for generation budget, it ties or falls behind self‑consistency sampling, with persona prompting actually reducing accuracy. The authors find that MAD’s benefits largely stem from the first answer exchange and that many reported gains are due to ensemble‑sampling effects rather than true diversity, highlighting the need for budget‑matched, contamination‑checked baselines.
whyItMatters":"The findings clarify that MAD’s perceived advantages may be overestimated and that future debate mechanisms must be evaluated against rigorous, budget‑matched baselines to ensure genuine performance improvements."
By Leonardo Ferreira, Gardenia Liu, Kaden Zheng
arXiv:2606. 29914v1 Announce Type: cross Abstract: Agent memory systems are increasingly evaluated against RAG and full-context baselines, but reported gains often mix changes in the memory method with changes in the language model, embedding model, or retrieval pipeline, making it unclear what is actually being measured.
By Kuan Wang
arXiv:2608. 13706v1 Announce Type: cross Abstract: Existing defenses against hallucination in retrieval-augmented and multi-agent pipelines remain partial: evidence is trusted despite modality disagreement, debate verifies an aggregate report rather than individual claims, and such verification occurs only after drafting, leaving inter-agent errors undetected until the final text.
By Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud, M. F. Mridha, Md. Alam Hossain