works on

From the 1 of 8 linked papers with an AI index.

collaborators

8 papers

cs.LG2026

Track, Rank, Crack: Epistemic Working Memory Scales Multi-Hop Reasoning in Language Agents

Ning Liu

The paper introduces SLEUTH, a system that gives language agents an explicit epistemic working memory to track confirmed facts, rank hypotheses, and manage open questions, improvin…

cs.LG2026

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

Ning Liu

Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits t…

cs.LG2026

Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution

Ning Liu, Kalle Kujanpää, Zhaoxuan Zhu +11

Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constr…

cs.CL2026

Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems

Kalle Kujanpää, Ning Liu, Shahnawaz Alam +4

Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an ag…

cs.LG2026

Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph

Ning Liu, Chuanneng Sun, Kristina Klinkner +1

Direct Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from h…

cs.LG2026

Rethinking Flexible Graph Similarity Computation: One-step Alignment with Global Guidance

Zhouyang Liu, Ning Liu, Yixin Chen +3

Graph Edit Distance (GED) is a widely used measure of graph similarity, valued for its flexibility in encoding domain knowledge through operation costs. However, existing learning-…