8 papers
Learning to Share: Selective Memory for Efficient Parallel Agentic Systems
Joseph Fioresi, Parth Parag Kulkarni, Ashmal Vayani +2
Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results. To improve robustness and solution qua…
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
Junhong Lin, Shicheng Liu, Jinyeop Song +3
Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide…
Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction
Yuanzhe Li, Jianing Deng, Jingtong Hu +3
Large language models (LLMs) achieve strong performance in long-horizon decision-making tasks through multi-step interaction and reasoning at test time. While practitioners commonl…
Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models
Junhong Lin, Xinyue Zeng, Jie Zhu +4
Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode…
How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
Junhong Lin, Bing Zhang, Song Wang +4
Large language models (LLMs) continue to struggle with knowledge-intensive questions that require up-to-date information and multi-hop reasoning. Augmenting LLMs with hybrid extern…
RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
Jialiang Zhu, Gongrui Zhang, Xiaolong Ma +17
LLM-based deep research agents are largely built on the ReAct framework. This linear design makes it difficult to revisit earlier states, branch into alternative search directions,…