5 papers
MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations
Yan Xu, Dandan Song, Luan Zhang +8
Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in completing complex tasks through multi-step reasoning and tool interactions. However, recent st…
PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces
Pyrros Koussios, Benjamin Jäger, John Hua Yao +3
Characterizing LLM reasoning remains an open challenge, as many existing benchmarks isolate specific reasoning skills, rely on external knowledge, or are costly to extend. We intro…
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
Luan Zhang, Ruochen Zhou, Dandan Song +9
Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable environments. Recent work has…
PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
Luan Zhang, Dandan Song, Zhijing Wu +8
Tool-integrated reasoning (TIR) enables large language models (LLMs) to enhance their capabilities by interacting with external tools, such as code interpreters (CI). Most recent s…
ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
Huipeng Ma, Luan Zhang, Dandan Song +10
In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query. However, these approaches are inher…