arXiv AI

Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents

arXiv AI
Nov 6

Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency

The paper investigates how different retrieval designs affect conversational agents. Three approaches are compared: skill-based retrieval in the main agent, a non‑persistent retrieval subagent that generates findings, and a persistent retrieval subagent that keeps history and returns evidence to the main agent. The persistent design reduces token usage and API cost by 43.3% and 45.0% respectively, cuts response time by 9.1%, and allows the main agent to request corrections from the subagent.

By Karthik Ravula, Sathwik Kowtha, Rishabh Verma, Kala Mehak Jain, Gunjit Mittal
arXiv AI
Sep 24

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

The paper introduces the concept of an agent’s "taste"—its ability to make effective long‑horizon decisions—and presents Taste‑Bench, a new benchmark that automatically generates decision‑fork questions from agent trajectories. Taste‑Bench evaluates models on choosing the best path without seeing future outcomes, revealing that top models answer only about 60% of questions correctly and that later‑appearing evidence makes forks harder. The authors also demonstrate that training a student model to mimic a teacher’s judgment improves decision quality and overall success on held‑out software engineering tasks.

By Wenbo Pan, Zhichao Liu, Shujie Liu, Jingying Zeng, Chin-Yew Lin, Xianfeng Tang, Yan Lu, Qi He, Xiaohua Jia
arXiv AI
Oct 28

Clearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers

The paper introduces FoG, a framework that trains knowledge graph (KG) agents to retrieve the evidence behind their answers. FoG combines evidence‑grounded synthesis, a KG interaction agent, and an evidence‑coverage process reward (ECPR) to ensure that every answer is supported by retrieved triples. Experiments on three KGQA benchmarks show that 3B–4B open‑source agents trained with FoG outperform larger baselines in both answer accuracy and evidence coverage, even with zero‑shot cross‑KG transfer.

By Zongyuan Sun, Shuai Zhao, Yingjun Du, Ke Shu, Ziyue Zhu, Haoran Luo
Hugging Face Trending Papers
Nov 5

Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency

The paper examines three retrieval designs for conversational agents: skill-based retrieval in the main agent, a non-persistent retrieval subagent that generates findings, and a persistent retrieval subagent that keeps retrieval history and returns evidence directly to the main agent. The persistent design reduces token usage by 43.3% and API cost by 45.0% compared to skill-based retrieval, while cutting average response time by 9.1%. Compared to non-persistent retrieval, it speeds up responses by 15.6 seconds per question but uses 65.1% more tokens and costs 29.1% more.

arXiv AI
Oct 26

Same Context, Different Agents: A Behavioral Study of Semantic Layers, Multi-Agent Orchestration and Memory Compaction in Data Agents

arXiv:2610.20959v2 Announce Type: replace-cross Abstract: Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this,...

By Zhivar Sourati, Marianne Menglin Liu, Zheng Wang, Rongguang Wang, Sai Ashish Somayajula, Tao Sheng, Kyu J. Han, Sujith Ravi, Dan Roth
arXiv AI
Oct 16

Same Context, Different Agents: A Behavioral Study of Semantic Layers, Orchestration and Compaction in Data Agents

The study examines how three context‑engineering techniques—semantic layers, orchestration, and compaction—affect data agents that answer questions over heterogeneous data. Using seven large language models on 1,514 long‑horizon tasks, the authors identify three agent behavior groups (investigators, premature answerers, early stoppers) and show that each technique benefits only the group it aligns with, while sometimes harming others. Combining the techniques yields smaller net gains than the sum of individual effects, leading to guidance on selecting techniques based on agent behavior, task demands, and accuracy‑cost trade‑offs.

By Zhivar Sourati, Marianne Menglin Liu, Zheng Wang, Rongguang Wang, Sai Ashish Somayajula, Tao Sheng, Kyu J. Han, Sujith Ravi, Dan Roth