Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we take a step forward by enabling models to collaborate directly within the continuous latent space. We introduce LatentMAS, an end-to-end training-free framework that enables pure latent collaboration among LLM agents. In LatentMAS, each agent first performs auto-regressive latent thoughts generation through last-layer hidden embeddings. A shared latent working memory then preserves and transfers each agent's internal representations, ensuring lossless information exchange. We provide theoretical analyses establishing that LatentMAS attains higher expressiveness and lossless information preservation with substantially lower complexity than vanilla text-based MAS. In addition, empirical evaluations across 9 comprehensive benchmarks spanning math and science reasoning, commonsense understanding, and code generation show that LatentMAS consistently outperforms strong single-model and text-based MAS baselines, achieving up to 14.6% higher accuracy, reducing output token usage by 70.8%-83.7%, and providing 4x-4.3x faster end-to-end inference. These results demonstrate that our new latent collaboration framework enhances system-level reasoning quality while offering substantial efficiency gains without any additional training. Code and data are fully open-sourced at https://github.com/Gen-Verse/LatentMAS.

ABSTRACT Multi-hop question answering is a challenging task in which language models must reason over multiple steps to reach the correct answer. With the help of Large Language Models and their reasoning capabilities, existing systems are able to think and decompose an input question over multiple steps to analyze, retrieve, and reason. However, training-based approaches for this problem still suffer from LLM hallucinations and incorrect reasoning paths that hinder performance. Hence, we propose P A THFINDER, an approach that: (i) uses Monte Carlo Tree Search to generate training path traces, (ii) improves training data quality by filtering erroneous and lengthy traces using sub-answer recall and LLM-as-a-judge verification, and (iii) reformulates sub-queries to handle failed retrieval cases. By following these steps, we demonstrate that P A THFINDER improves the performance of multi-hop QA over public benchmark datasets. Index T erms-- multi-hop question answering, retrieval augmented generation, reasoning, large language models 1. INTRODUCTION Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning-intensive tasks.

This paper presents a question answering system that operates exclusively on a knowledge graph retrieval without relying on retrieval augmented generation (RAG) with large language models (LLMs). Instead, a small paraphraser model is used to paraphrase the entity relationship edges retrieved from querying the knowledge graph. The proposed pipeline is divided into two main stages. The first stage involves pre-processing a document to generate sets of question-answer (QA) pairs. The second stage converts these QAs into a knowledge graph from which graph-based retrieval is performed using embeddings and fuzzy techniques. The graph is queried, re-ranked, and paraphrased to generate a final answer. This work includes an evaluation using LLM-as-a-judge on the CRAG benchmark, which resulted in accuracies of 71.9% and 54.4% using LLAMA-3.2 and GPT-3.5-Turbo,

-- India is an agro-based economy and proper information about agricultural practices is the key to optimal agricultural growth and output. In order to answer the queries of the farmer, we have build an agricultural chatbot based on the dataset from Kisan Call Center. This system is robust enough to answer queries related to weather, market rates, plant protection and government schemes. This system is available 24*7, can be accessed through any electronic device and the information is delivered with the ease of understanding. The system is based on a sentence embedding model which gives an accuracy of 56%. With such a system, farmers can progress towards easier information about farming related practices and hence a better agricultural output. The job of the Call Center workforce would be made easier and the hard work of various such workers can be redirected to a better goal. In India, agriculture plays an important role in the economic development by contributing about 16% to the overall GDP and accounting for employment of approximately 52% of the Indian population[12].

Estimating the difficulty of input questions as perceived by large language models (LLMs) is essential for accurate performance evaluation and adaptive inference. Existing methods typically rely on repeated response sampling, auxiliary models, or fine-tuning the target model itself, which may incur substantial computational costs or compromise generality. In this paper, we propose a novel approach for difficulty estimation that leverages only the hidden representations produced by the target LLM. We model the token-level generation process as a Markov chain and define a value function to estimate the expected output quality given any hidden state. This allows for efficient and accurate difficulty estimation based solely on the initial hidden state, without generating any output tokens. Extensive experiments across both textual and multimodal tasks demonstrate that our method consistently outperforms existing baselines in difficulty estimation. Moreover, we apply our difficulty estimates to guide adaptive reasoning strategies, including Self-Consistency, Best-of-N, and Self-Refine, achieving higher inference efficiency with fewer generated tokens.

This paper describes our participation in SemEval 2025 Task 8, focused on Tabular Question Answering. We developed a zero-shot pipeline that leverages an Large Language Model to generate functional code capable of extracting the relevant information from tabular data based on an input question. Our approach consists of a modular pipeline where the main code generator module is supported by additional components that identify the most relevant columns and analyze their data types to improve extraction accuracy. In the event that the generated code fails, an iterative refinement process is triggered, incorporating the error feedback into a new generation prompt to enhance robustness. Our results show that zero-shot code generation is a valid approach for Tabular QA, achieving rank 33 of 53 in the test phase despite the lack of task-specific fine-tuning.

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks by effectively utilizing a prompting strategy. However, they are highly sensitive to input perturbations, such as typographical errors or slight character order errors, which can substantially degrade their performance. Despite advances in prompting techniques, developing a prompting strategy that explicitly mitigates the negative impact of such perturbations remains an open challenge. To bridge this gap, we propose Robustness of Prompting (RoP), a novel prompting strategy specifically designed to enhance the robustness of LLMs. RoP consists of two stages: Error Correction and Guidance. In the Error Correction stage, RoP applies diverse perturbation methods to generate adversarial examples, which are then used to construct prompts that automatically correct input errors. In the Guidance stage, RoP generates an optimal guidance prompting based on the corrected input, steering the model toward more robust and accurate inferences. Through comprehensive experiments spanning arithmetic, commonsense, and logical reasoning tasks, we demonstrate that RoP significantly improves LLMs' robustness against adversarial perturbations. Notably, it maintains model accuracy with only minimal degradation compared to clean input scenarios, thereby establishing RoP as a practical and effective approach for enhancing LLM robustness in real-world applications.

Retrieval-Augmented Generation (RAG) systems are increasingly diverse, yet many suffer from monolithic designs that tightly couple core functions like query reformulation, retrieval, reasoning, and verification. This limits their interpretability, systematic evaluation, and targeted improvement, especially for complex multi-hop question answering. We introduce ComposeRAG, a novel modular abstraction that decomposes RAG pipelines into atomic, composable modules. Each module, such as Question Decomposition, Query Rewriting, Retrieval Decision, and Answer Verification, acts as a parameterized transformation on structured inputs/outputs, allowing independent implementation, upgrade, and analysis. To enhance robustness against errors in multi-step reasoning, ComposeRAG incorporates a self-reflection mechanism that iteratively revisits and refines earlier steps upon verification failure. Evaluated on four challenging multi-hop QA benchmarks, ComposeRAG consistently outperforms strong baselines in both accuracy and grounding fidelity. Specifically, it achieves up to a 15% accuracy improvement over fine-tuning-based methods and up to a 5% gain over reasoning-specialized pipelines under identical retrieval conditions. Crucially, ComposeRAG significantly enhances grounding: its verification-first design reduces ungrounded answers by over 10% in low-quality retrieval settings, and by approximately 3% even with strong corpora. Comprehensive ablation studies validate the modular architecture, demonstrating distinct and additive contributions from each component. These findings underscore ComposeRAG's capacity to deliver flexible, transparent, scalable, and high-performing multi-hop reasoning with improved grounding and interpretability.

Locating specific segments within an instructional video is an efficient way to acquire guiding knowledge. Generally, the task of obtaining video segments for both verbal explanations and visual demonstrations is known as visual answer localization (VAL). However, users often need multiple interactions to obtain answers that align with their expectations when using the system. During these interactions, humans deepen their understanding of the video content by asking themselves questions, thereby accurately identifying the location. Therefore, we propose a new task, named In-VAL, to simulate the multiple interactions between humans and videos in the procedure of obtaining visual answers. The In-VAL task requires interactively addressing several semantic gap issues, including 1) the ambiguity of user intent in the input questions, 2) the incompleteness of language in video subtitles, and 3) the fragmentation of content in video segments. To address these issues, we propose Ask2Loc, a framework for resolving In-VAL by asking questions. It includes three key modules: 1) a chatting module to refine initial questions and uncover clear intentions, 2) a rewriting module to generate fluent language and create complete descriptions, and 3) a searching module to broaden local context and provide integrated content. We conduct extensive experiments on three reconstructed In-VAL datasets. Compared to traditional end-to-end and two-stage methods, our proposed Ask2Loc can improve performance by up to 14.91 (mIoU) on the In-VAL task. Our code and datasets can be accessed at https://github.com/changzong/Ask2Loc.

Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. As current KBQA methods struggle with unseen knowledge base elements at test time,we introduce SG-KBQA: a novel model that injects schema contexts into entity retrieval and logical form generation to tackle this issue. It uses the richer semantics and awareness of the knowledge base structure provided by schema contexts to enhance generalizability. We show that SG-KBQA achieves strong generalizability, outperforming state-of-the-art models on two commonly used benchmark datasets across a variety of test settings. Code will be released upon paper publication.