TJS Articles & News

BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documentscs.AI updates on arXiv.org arXiv:2512.03413v1 Announce Type: cross
Abstract: As an effective method to boost the performance of Large Language Models (LLMs) on the question answering (QA) task, Retrieval-Augmented Generation (RAG), which queries highly relevant information from external complex documents, has attracted tremendous attention from both industry and academia. Existing RAG approaches often focus on general documents, and they overlook the fact that many real-world documents (such as books, booklets, handbooks, etc.) have a hierarchical structure, which organizes their content from different granularity levels, leading to poor performance for the QA task. To address these limitations, we introduce BookRAG, a novel RAG approach targeted for documents with a hierarchical structure, which exploits logical hierarchies and traces entity relations to query the highly relevant information. Specifically, we build a novel index structure, called BookIndex, by extracting a hierarchical tree from the document, which serves as the role of its table of contents, using a graph to capture the intricate relationships between entities, and mapping entities to tree nodes. Leveraging the BookIndex, we then propose an agent-based query method inspired by the Information Foraging Theory, which dynamically classifies queries and employs a tailored retrieval workflow. Extensive experiments on three widely adopted benchmarks demonstrate that BookRAG achieves state-of-the-art performance, significantly outperforming baselines in both retrieval recall and QA accuracy while maintaining competitive efficiency.

 arXiv:2512.03413v1 Announce Type: cross
Abstract: As an effective method to boost the performance of Large Language Models (LLMs) on the question answering (QA) task, Retrieval-Augmented Generation (RAG), which queries highly relevant information from external complex documents, has attracted tremendous attention from both industry and academia. Existing RAG approaches often focus on general documents, and they overlook the fact that many real-world documents (such as books, booklets, handbooks, etc.) have a hierarchical structure, which organizes their content from different granularity levels, leading to poor performance for the QA task. To address these limitations, we introduce BookRAG, a novel RAG approach targeted for documents with a hierarchical structure, which exploits logical hierarchies and traces entity relations to query the highly relevant information. Specifically, we build a novel index structure, called BookIndex, by extracting a hierarchical tree from the document, which serves as the role of its table of contents, using a graph to capture the intricate relationships between entities, and mapping entities to tree nodes. Leveraging the BookIndex, we then propose an agent-based query method inspired by the Information Foraging Theory, which dynamically classifies queries and employs a tailored retrieval workflow. Extensive experiments on three widely adopted benchmarks demonstrate that BookRAG achieves state-of-the-art performance, significantly outperforming baselines in both retrieval recall and QA accuracy while maintaining competitive efficiency. Read More  

ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithmscs.AI updates on arXiv.org arXiv:2512.03476v1 Announce Type: cross
Abstract: Bridging the gap between theoretical conceptualization and computational implementation is a major bottleneck in Scientific Computing (SciC) and Scientific Machine Learning (SciML). We introduce ATHENA (Agentic Team for Hierarchical Evolutionary Numerical Algorithms), an agentic framework designed as an Autonomous Lab to manage the end-to-end computational research lifecycle. Its core is the HENA loop, a knowledge-driven diagnostic process framed as a Contextual Bandit problem. Acting as an online learner, the system analyzes prior trials to select structural `actions’ ($A_n$) from combinatorial spaces guided by expert blueprints (e.g., Universal Approximation, Physics-Informed constraints). These actions are translated into executable code ($S_n$) to generate scientific rewards ($R_n$). ATHENA transcends standard automation: in SciC, it autonomously identifies mathematical symmetries for exact analytical solutions or derives stable numerical solvers where foundation models fail. In SciML, it performs deep diagnosis to tackle ill-posed formulations and combines hybrid symbolic-numeric workflows (e.g., coupling PINNs with FEM) to resolve multiphysics problems. The framework achieves super-human performance, reaching validation errors of $10^{-14}$. Furthermore, collaborative “human-in-the-loop” intervention allows the system to bridge stability gaps, improving results by an order of magnitude. This paradigm shift focuses from implementation mechanics to methodological innovation, accelerating scientific discovery.

 arXiv:2512.03476v1 Announce Type: cross
Abstract: Bridging the gap between theoretical conceptualization and computational implementation is a major bottleneck in Scientific Computing (SciC) and Scientific Machine Learning (SciML). We introduce ATHENA (Agentic Team for Hierarchical Evolutionary Numerical Algorithms), an agentic framework designed as an Autonomous Lab to manage the end-to-end computational research lifecycle. Its core is the HENA loop, a knowledge-driven diagnostic process framed as a Contextual Bandit problem. Acting as an online learner, the system analyzes prior trials to select structural `actions’ ($A_n$) from combinatorial spaces guided by expert blueprints (e.g., Universal Approximation, Physics-Informed constraints). These actions are translated into executable code ($S_n$) to generate scientific rewards ($R_n$). ATHENA transcends standard automation: in SciC, it autonomously identifies mathematical symmetries for exact analytical solutions or derives stable numerical solvers where foundation models fail. In SciML, it performs deep diagnosis to tackle ill-posed formulations and combines hybrid symbolic-numeric workflows (e.g., coupling PINNs with FEM) to resolve multiphysics problems. The framework achieves super-human performance, reaching validation errors of $10^{-14}$. Furthermore, collaborative “human-in-the-loop” intervention allows the system to bridge stability gaps, improving results by an order of magnitude. This paradigm shift focuses from implementation mechanics to methodological innovation, accelerating scientific discovery. Read More  

Multi-Agent Reinforcement Learning with Communication-Constrained Priorscs.AI updates on arXiv.org arXiv:2512.03528v1 Announce Type: new
Abstract: Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems. However, in most real-world scenarios, lossy communication is a prevalent issue. Existing multi-agent reinforcement learning with communication, due to their limited scalability and robustness, struggles to apply to complex and dynamic real-world environments. To address these challenges, we propose a generalized communication-constrained model to uniformly characterize communication conditions across different scenarios. Based on this, we utilize it as a learning prior to distinguish between lossy and lossless messages for specific scenarios. Additionally, we decouple the impact of lossy and lossless messages on distributed decision-making, drawing on a dual mutual information estimatior, and introduce a communication-constrained multi-agent reinforcement learning framework, quantifying the impact of communication messages into the global reward. Finally, we validate the effectiveness of our approach across several communication-constrained benchmarks.

 arXiv:2512.03528v1 Announce Type: new
Abstract: Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems. However, in most real-world scenarios, lossy communication is a prevalent issue. Existing multi-agent reinforcement learning with communication, due to their limited scalability and robustness, struggles to apply to complex and dynamic real-world environments. To address these challenges, we propose a generalized communication-constrained model to uniformly characterize communication conditions across different scenarios. Based on this, we utilize it as a learning prior to distinguish between lossy and lossless messages for specific scenarios. Additionally, we decouple the impact of lossy and lossless messages on distributed decision-making, drawing on a dual mutual information estimatior, and introduce a communication-constrained multi-agent reinforcement learning framework, quantifying the impact of communication messages into the global reward. Finally, we validate the effectiveness of our approach across several communication-constrained benchmarks. Read More  

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordiacs.AI updates on arXiv.org arXiv:2512.03318v1 Announce Type: new
Abstract: Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent’s ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

 arXiv:2512.03318v1 Announce Type: new
Abstract: Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent’s ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement. Read More  

SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Modelscs.AI updates on arXiv.org arXiv:2506.05745v2 Announce Type: replace
Abstract: Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce SPRINT, a novel post-training and inference-time framework designed to enable LRMs to dynamically identify and exploit opportunities for parallelization during their reasoning process. SPRINT incorporates an innovative data curation pipeline that reorganizes natural language reasoning trajectories into structured rounds of long-horizon planning and parallel execution. By fine-tuning LRMs on a small amount of such curated data, the models learn to dynamically identify independent subtasks within extended reasoning processes and effectively execute them in parallel. Through extensive evaluations, we demonstrate that models fine-tuned with the SPRINT framework match the performance of reasoning models on complex domains such as mathematics while generating up to 39% fewer sequential tokens on problems requiring more than 8,000 output tokens. Finally, we observe consistent results transferred to two out-of-distribution tasks, namely GPQA and Countdown, with up to 45% and 65% reduction in average sequential tokens respectively for longer reasoning trajectories, while matching the performance of the fine-tuned reasoning model.

 arXiv:2506.05745v2 Announce Type: replace
Abstract: Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce SPRINT, a novel post-training and inference-time framework designed to enable LRMs to dynamically identify and exploit opportunities for parallelization during their reasoning process. SPRINT incorporates an innovative data curation pipeline that reorganizes natural language reasoning trajectories into structured rounds of long-horizon planning and parallel execution. By fine-tuning LRMs on a small amount of such curated data, the models learn to dynamically identify independent subtasks within extended reasoning processes and effectively execute them in parallel. Through extensive evaluations, we demonstrate that models fine-tuned with the SPRINT framework match the performance of reasoning models on complex domains such as mathematics while generating up to 39% fewer sequential tokens on problems requiring more than 8,000 output tokens. Finally, we observe consistent results transferred to two out-of-distribution tasks, namely GPQA and Countdown, with up to 45% and 65% reduction in average sequential tokens respectively for longer reasoning trajectories, while matching the performance of the fine-tuned reasoning model. Read More  

Multimodal Reinforcement Learning with Agentic Verifier for AI Agentscs.AI updates on arXiv.org arXiv:2512.03438v1 Announce Type: new
Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer rewards computed from the reasoning tokens can improve learning significantly by providing more fine-grained guidance. However, it is challenging to compute more informative rewards in MMRL beyond those based on outcomes since different samples may require different scoring functions and teacher models may provide noisy reward signals too. In this paper, we introduce the Argos (Agentic Reward for Grounded & Objective Scoring), a principled reward agent to train multimodal reasoning models for agentic tasks. For each sample, Argos selects from a pool of teacher-model derived and rule-based scoring functions to simultaneously evaluate: (i) final response accuracy, (ii) spatiotemporal localization of referred entities and actions, and (iii) the quality of the reasoning process. We find that by leveraging our agentic verifier across both SFT data curation and RL training, our model achieves state-of-the-art results across multiple agentic tasks such as spatial reasoning, visual hallucination as well as robotics and embodied AI benchmarks. Critically, we demonstrate that just relying on SFT post-training on highly curated reasoning data is insufficient, as agents invariably collapse to ungrounded solutions during RL without our online verification. We also show that our agentic verifier can help to reduce reward-hacking in MMRL. Finally, we also provide a theoretical justification for the effectiveness of Argos through the concept of pareto-optimality.

 arXiv:2512.03438v1 Announce Type: new
Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer rewards computed from the reasoning tokens can improve learning significantly by providing more fine-grained guidance. However, it is challenging to compute more informative rewards in MMRL beyond those based on outcomes since different samples may require different scoring functions and teacher models may provide noisy reward signals too. In this paper, we introduce the Argos (Agentic Reward for Grounded & Objective Scoring), a principled reward agent to train multimodal reasoning models for agentic tasks. For each sample, Argos selects from a pool of teacher-model derived and rule-based scoring functions to simultaneously evaluate: (i) final response accuracy, (ii) spatiotemporal localization of referred entities and actions, and (iii) the quality of the reasoning process. We find that by leveraging our agentic verifier across both SFT data curation and RL training, our model achieves state-of-the-art results across multiple agentic tasks such as spatial reasoning, visual hallucination as well as robotics and embodied AI benchmarks. Critically, we demonstrate that just relying on SFT post-training on highly curated reasoning data is insufficient, as agents invariably collapse to ungrounded solutions during RL without our online verification. We also show that our agentic verifier can help to reduce reward-hacking in MMRL. Finally, we also provide a theoretical justification for the effectiveness of Argos through the concept of pareto-optimality. Read More  

PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Taskscs.AI updates on arXiv.org arXiv:2512.03549v1 Announce Type: new
Abstract: We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work.

 arXiv:2512.03549v1 Announce Type: new
Abstract: We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work. Read More  

AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Constructioncs.AI updates on arXiv.org arXiv:2503.13430v2 Announce Type: replace-cross
Abstract: Autonomous driving requires understanding infrastructure elements, such as lanes and crosswalks. To navigate safely, this understanding must be derived from sensor data in real-time and needs to be represented in vectorized form. Learned Bird’s-Eye View (BEV) encoders are commonly used to combine a set of camera images from multiple views into one joint latent BEV grid. Traditionally, from this latent space, an intermediate raster map is predicted, providing dense spatial supervision but requiring post-processing into the desired vectorized form. More recent models directly derive infrastructure elements as polylines using vectorized map decoders, providing instance-level information. Our approach, Augmentation Map Network (AugMapNet), proposes latent BEV feature grid augmentation, a novel technique that significantly enhances the latent BEV representation. AugMapNet combines vector decoding and dense spatial supervision more effectively than existing architectures while remaining easy to integrate compared to other hybrid approaches. It additionally benefits from extra processing on its latent BEV features. Experiments on nuScenes and Argoverse2 datasets demonstrate significant improvements on vectorized map prediction of up to 13.3% over the StreamMapNet baseline on 60 m range and greater improvements on larger ranges. We confirm transferability by applying our method to another baseline, SQD-MapNet, and find similar improvements. A detailed analysis of the latent BEV grid confirms a more structured latent space of AugMapNet and shows the value of our novel concept beyond pure performance improvement. The code can be found at https://github.com/tmonnin/augmapnet

 arXiv:2503.13430v2 Announce Type: replace-cross
Abstract: Autonomous driving requires understanding infrastructure elements, such as lanes and crosswalks. To navigate safely, this understanding must be derived from sensor data in real-time and needs to be represented in vectorized form. Learned Bird’s-Eye View (BEV) encoders are commonly used to combine a set of camera images from multiple views into one joint latent BEV grid. Traditionally, from this latent space, an intermediate raster map is predicted, providing dense spatial supervision but requiring post-processing into the desired vectorized form. More recent models directly derive infrastructure elements as polylines using vectorized map decoders, providing instance-level information. Our approach, Augmentation Map Network (AugMapNet), proposes latent BEV feature grid augmentation, a novel technique that significantly enhances the latent BEV representation. AugMapNet combines vector decoding and dense spatial supervision more effectively than existing architectures while remaining easy to integrate compared to other hybrid approaches. It additionally benefits from extra processing on its latent BEV features. Experiments on nuScenes and Argoverse2 datasets demonstrate significant improvements on vectorized map prediction of up to 13.3% over the StreamMapNet baseline on 60 m range and greater improvements on larger ranges. We confirm transferability by applying our method to another baseline, SQD-MapNet, and find similar improvements. A detailed analysis of the latent BEV grid confirms a more structured latent space of AugMapNet and shows the value of our novel concept beyond pure performance improvement. The code can be found at https://github.com/tmonnin/augmapnet Read More  

A Learning-based Control Methodology for Transitioning VTOL UAVscs.AI updates on arXiv.org arXiv:2512.03548v1 Announce Type: cross
Abstract: Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the center of gravity and thrust direction during transitions. Current control methods’ decoupled control of altitude and position leads to significant vibration, and limits interaction consideration and adaptability. In this study, we propose a novel coupled transition control methodology based on reinforcement learning (RL) driven controller. Besides, contrasting to the conventional phase-transition approach, the ST3M method demonstrates a new perspective by treating cruise mode as a special case of hover. We validate the feasibility of applying our method in simulation and real-world environments, demonstrating efficient controller development and migration while accurately controlling UAV position and attitude, exhibiting outstanding trajectory tracking and reduced vibrations during the transition process.

 arXiv:2512.03548v1 Announce Type: cross
Abstract: Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the center of gravity and thrust direction during transitions. Current control methods’ decoupled control of altitude and position leads to significant vibration, and limits interaction consideration and adaptability. In this study, we propose a novel coupled transition control methodology based on reinforcement learning (RL) driven controller. Besides, contrasting to the conventional phase-transition approach, the ST3M method demonstrates a new perspective by treating cruise mode as a special case of hover. We validate the feasibility of applying our method in simulation and real-world environments, demonstrating efficient controller development and migration while accurately controlling UAV position and attitude, exhibiting outstanding trajectory tracking and reduced vibrations during the transition process. Read More