Artyom Sorokin

Petr Anokhin, Nikita Semenov, Artyom Sorokin et al.

Advancements in the capabilities of Large Language Models (LLMs) have created a promising foundation for developing autonomous agents. With the right tools, these agents could learn to solve tasks in new environments by accumulating and updating their knowledge. Current LLM-based agents process past experiences using a full history of observations, summarization, retrieval augmentation. However, these unstructured memory representations do not facilitate the reasoning and planning essential for complex decision-making. In our study, we introduce AriGraph, a novel method wherein the agent constructs and updates a memory graph that integrates semantic and episodic memories while exploring the environment. We demonstrate that our Ariadne LLM agent, consisting of the proposed memory architecture augmented with planning and decision-making, effectively handles complex tasks within interactive text game environments difficult even for human players. Results show that our approach markedly outperforms other established memory methods and strong RL baselines in a range of problems of varying complexity. Additionally, AriGraph demonstrates competitive performance compared to dedicated knowledge graph-based methods in static multi-hop question-answering.

Artyom Sorokin, Nazar Buzun, Leonid Pugachev et al.

In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application of gradient based training requires intermediate computations to be stored for every element of a sequence. This requires to store prohibitively large intermediate data if a sequence consists of thousands or even millions elements, and as a result, makes learning of very long-term dependencies infeasible. However, the majority of sequence elements can usually be predicted by taking into account only temporally local information. On the other hand, predictions affected by long-term dependencies are sparse and characterized by high uncertainty given only local information. We propose MemUP, a new training method that allows to learn long-term dependencies without backpropagating gradients through the whole sequence at a time. This method can potentially be applied to any recurrent architecture. LSTM network trained with MemUP performs better or comparable to baselines while requiring to store less intermediate data.

Artyom Sorokin, Nazar Buzun, Alexander Anokhin et al.

Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most existing RAG methods focus on single-step retrieval, which is often insufficient for answering complex questions that require multi-step search. Recently, multi-step retrieval approaches have emerged, typically involving the fine-tuning of small LLMs to perform multi-step retrieval. This type of fine-tuning is highly resource-intensive and does not enable the use of larger LLMs. In this work, we propose Q-RAG, a novel approach that fine-tunes the Embedder model for multi-step retrieval using reinforcement learning (RL). Q-RAG offers a competitive, resource-efficient alternative to existing multi-step retrieval methods for open-domain question answering and achieves state-of-the-art results on the popular long-context benchmarks Babilong and RULER for contexts up to 10M tokens.

Petr Anokhin, Roman Khalikov, Stefan Rebrikov et al.

Large language models (LLMs) have shown remarkable capabilities in isolated step-by-step reasoning tasks such as mathematics and programming, but their proficiency in long-horizon planning, where solutions require extended, structured sequences of interdependent actions, remains underexplored. Existing benchmarks typically assess LLMs through abstract or low-dimensional algorithmic tasks, failing to capture the complexity of realistic planning environments. We introduce HeroBench, a novel benchmark designed specifically to evaluate long-horizon planning and structured reasoning within complex RPG-inspired virtual worlds. HeroBench provides a rigorously constructed dataset of tasks covering a wide range of difficulties, a simulated environment to execute and validate agent plans, and detailed analytical tools for evaluating model performance. Tasks challenge models to formulate strategic plans, efficiently gather resources, master necessary skills, craft equipment, and defeat adversaries, reflecting practical scenarios' layered dependencies and constraints. Our extensive evaluation of 25 state-of-the-art LLMs, spanning both open-source and proprietary models, including the GPT-5 family, reveals substantial performance disparities rarely observed in conventional reasoning benchmarks. Detailed error analysis further uncovers specific weaknesses in current models' abilities to generate robust high-level plans and reliably execute structured actions. HeroBench thus not only significantly advances the evaluation of LLM reasoning but also provides a flexible, scalable foundation for future research into advanced, autonomous planning in virtual environments.

Yuri Kuratov, Aydar Bulatov, Petr Anokhin et al.

This paper addresses the challenge of processing long documents using generative transformer models. To evaluate different approaches, we introduce BABILong, a new benchmark designed to assess model capabilities in extracting and processing distributed facts within extensive texts. Our evaluation, which includes benchmarks for GPT-4 and RAG, reveals that common methods are effective only for sequences up to $10^4$ elements. In contrast, fine-tuning GPT-2 with recurrent memory augmentations enables it to handle tasks involving up to $11\times 10^6$ elements. This achievement marks a substantial leap, as it is by far the longest input processed by any neural network model to date, demonstrating a significant improvement in the processing capabilities for long sequences.

Yuri Kuratov, Aydar Bulatov, Petr Anokhin et al.

In recent years, the input context sizes of large language models (LLMs) have increased dramatically. However, existing evaluation methods have not kept pace, failing to comprehensively assess the efficiency of models in handling long contexts. To bridge this gap, we introduce the BABILong benchmark, designed to test language models' ability to reason across facts distributed in extremely long documents. BABILong includes a diverse set of 20 reasoning tasks, including fact chaining, simple induction, deduction, counting, and handling lists/sets. These tasks are challenging on their own, and even more demanding when the required facts are scattered across long natural text. Our evaluations show that popular LLMs effectively utilize only 10-20\% of the context and their performance declines sharply with increased reasoning complexity. Among alternatives to in-context reasoning, Retrieval-Augmented Generation methods achieve a modest 60\% accuracy on single-fact question answering, independent of context length. Among context extension methods, the highest performance is demonstrated by recurrent memory transformers after fine-tuning, enabling the processing of lengths up to 50 million tokens. The BABILong benchmark is extendable to any length to support the evaluation of new upcoming models with increased capabilities, and we provide splits up to 10 million token lengths.