Related papers: MAVEN: Multi-Agent Verification-Elaboration Networ…

Multimodal LLMs are turning their focus to video benchmarks, however most video benchmarks only provide outcome supervision, with no intermediate or interpretable reasoning steps. This makes it challenging to assess if models are truly able…

LLM-as-Judge has emerged as a scalable alternative to human evaluation, enabling large language models (LLMs) to provide reward signals in trainings. While recent work has explored multi-agent extensions such as multi-agent debate and…

Analogical reasoning lies at the core of human cognition and remains a fundamental challenge for artificial intelligence. Raven's Progressive Matrices (RPM) serve as a widely used benchmark to assess abstract reasoning by requiring the…

Test-time reasoning architectures such as those following the Generate-Verify paradigm, where a model iteratively refines or verifies its own generated outputs, prioritise generation and verification but exclude the monitoring processes…

Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability. Recently, process-level reward models (PRMs) were proposed to…

The evolution of Large Language Models (LLMs) from static instruction-followers to autonomous agents necessitates operating within complex, stateful environments to achieve precise state-transition objectives. However, this paradigm is…

LLMs have demonstrated significant potential in quantitative finance by processing vast unstructured data to emulate human-like analytical workflows. However, current LLM-based methods primarily follow either an Asset-Centric paradigm…

Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound. We identify a root cause shared by both major mitigation paradigms (agent-based debate and retrieval…

Retrieval-augmented Generation (RAG) has demonstrated potential in enhancing medical question-answering systems through the integration of large language models (LLMs) with external medical literature. LLMs can retrieve relevant medical…

The advent of large language models (LLMs) has facilitated the development of natural language text generation. It also poses unprecedented challenges, with content hallucination emerging as a significant concern. Existing solutions often…

When copies of the same language model are prompted to debate, they produce diverse phrasings of one perspective rather than diverse perspectives. Multi-agent debate (MAD), and more broadly closed-system reasoning where agents iteratively…

Motivated by the underspecified, multi-hop nature of search queries and the multimodal, heterogeneous, and often conflicting nature of real-world web results, we introduce MERRIN (Multimodal Evidence Retrieval and Reasoning in Noisy Web…

Large reasoning models, often post-trained on long chain-of-thought (long CoT) data with reinforcement learning, achieve state-of-the-art performance on mathematical, coding, and domain-specific reasoning benchmarks. However, their logical…

Recent attempts to integrate large language models (LLMs) into recommender systems have gained momentum, but most remain limited to simple text generation or static prompt-based inference, failing to capture the complexity of user…

Multi-entity question answering (MEQA) represents significant challenges for large language models (LLM) and retrieval-augmented generation (RAG) systems, which frequently struggle to consolidate scattered information across diverse…

Algorithmic problem solving serves as a rigorous testbed for evaluating structured reasoning in AI coding systems, as it directly reflects a model's ability to perform structured reasoning in complex scenarios. Existing approaches…

Reliable uncertainty quantification (UQ) is essential in medical AI. Evidential Deep Learning (EDL) offers a computationally efficient way to quantify model uncertainty alongside predictions, unlike traditional methods such as Monte Carlo…

Existing Grammatical Error Correction (GEC) systems suffer from limited reference diversity, leading to underestimated evaluation and restricted model generalization. To address this issue, we introduce the Judge of Edit-Level Validity…

Multi-agent debate (MAD) systems improve LLM reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final agent decisions are compromised on erroneous reasoning. Existing methods lack…

Autonomous aerial systems increasingly rely on large language models (LLMs) for mission planning, perception, and decision-making, yet the lack of standardized and physically grounded benchmarks limits systematic evaluation of their…