Related papers: TRUST Agents: A Collaborative Multi-Agent Framewor…
The application of language models to project-level vulnerability detection remains challenging, owing to the dual requirement of accurately localizing security-sensitive code and correctly correlating and reasoning over complex program…
Reliable detection of deceptive behavior in Large Language Model (LLM) agents is an essential prerequisite for safe deployment in high-stakes agentic contexts. Prior work on scheming detection has focused exclusively on black-box monitors…
In multi-agent IR pipelines for tasks such as search and ranking, LLM-based agents exchange intermediate reasoning in terms of Chain-of-Thought (CoT) with each other. Current CoT evaluation narrowly focuses on target task accuracy. However,…
With the rise of generative AI, automated fact-checking methods to combat misinformation are becoming more and more important. However, factual claim detection, the first step in a fact-checking pipeline, suffers from two key issues that…
Verifying the success of computer use agent (CUA) trajectories is a critical challenge: without reliable verification, neither evaluation nor training signal can be trusted. In this paper, we present lessons learned from building a…
As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human oversight. While linear probes on model activations have shown promise for detecting…
Automatic fact verification has received significant attention recently. Contemporary automatic fact-checking systems focus on estimating truthfulness using numerical scores which are not human-interpretable. A human fact-checker generally…
Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…
The exponential growth of scientific literature poses unprecedented challenges for researchers attempting to synthesize knowledge across rapidly evolving fields. We present \textbf{Agentic AutoSurvey}, a multi-agent framework for automated…
A fundamental problem in data fusion is to determine the veracity of multi-source data in order to resolve conflicts. While previous work in truth discovery has proved to be useful in practice for specific settings, sources' behavior or…
With the rapid evolution of Large Language Models (LLMs), LLM-based agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems. This evolution stems from empowering LLMs with additional modules such…
In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…
Fake information poses one of the major threats for society in the 21st century. Identifying misinformation has become a key challenge due to the amount of fake news that is published daily. Yet, no approach is established that addresses…
Evaluating the veracity of everyday claims is time consuming and in some cases requires domain expertise. We empirically demonstrate that the commonly used fact checking pipeline, known as the retriever-reader, suffers from performance…
Explainable Reinforcement Learning (XRL) has emerged as a promising approach in improving the transparency of Reinforcement Learning (RL) agents. However, there remains a gap between complex RL policies and domain experts, due to the…
We present Prover Agent, a novel AI agent for automated theorem proving that integrates large language models (LLMs) with a formal proof assistant, Lean. Prover Agent coordinates an informal reasoning LLM, a formal prover model, and…
Long-horizon reasoning in LLM-based agents often fails not from generative weakness but from insufficient verification of intermediate reasoning. Co-Sight addresses this challenge by turning reasoning into a falsifiable and auditable…
The rapid propagation of misinformation poses substantial risks to public interest. To combat misinformation, large language models (LLMs) are adapted to automatically verify claim credibility. Nevertheless, existing methods heavily rely on…
Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used. Natural language is interpretable but vulnerable to semantic drift, while learned protocols…
Fact verification (FV) aims to assess the veracity of a claim based on relevant evidence. The traditional approach for automated FV includes a three-part pipeline relying on short evidence snippets and encoder-only inference models. More…