Large Language Model (LLM)-based agents that plan, use tools and act has begun to shape healthcare and medicine. Reported studies demonstrate competence on various tasks ranging from EHR analysis and differential diagnosis to treatment planning and research workflows. Yet the literature largely consists of overviews which are either broad surveys or narrow dives into a single capability (e.g., memory, planning, reasoning), leaving healthcare work without a common frame. We address this by reviewing 49 studies using a seven-dimensional taxonomy: Cognitive Capabilities, Knowledge Management, Interaction Patterns, Adaptation & Learning, Safety & Ethics, Framework Typology and Core Tasks & Subtasks with 29 operational sub-dimensions. Using explicit inclusion and exclusion criteria and a labeling rubric (Fully Implemented, Partially Implemented, Not Implemented), we map each study to the taxonomy and report quantitative summaries of capability prevalence and co-occurrence patterns. Our empirical analysis surfaces clear asymmetries. For instance, the External Knowledge Integration sub-dimension under Knowledge Management is commonly realized (~76% Fully Implemented) whereas Event-Triggered Activation sub-dimenison under Interaction Patterns is largely absent (~92% Not Implemented) and Drift Detection & Mitigation sub-dimension under Adaptation & Learning is rare (~98% Not Implemented). Architecturally, Multi-Agent Design sub-dimension under Framework Typology is the dominant pattern (~82% Fully Implemented) while orchestration layers remain mostly partial. Across Core Tasks & Subtasks, information centric capabilities lead e.g., Medical Question Answering & Decision Support and Benchmarking & Simulation, while action and discovery oriented areas such as Treatment Planning & Prescription still show substantial gaps (~59% Not Implemented).
The introduction of large language models ignited great retooling and rethinking of the software development models. The ensuing response of software engineering research yielded a massive body of tools and approaches. In this paper, we join the hassle by introducing agentic AI solutions for two tasks. First, we developed a solution for automatic test scenario generation from a detailed requirements description. This approach relies on specialized worker agents forming a star topology with the supervisor agent in the middle. We demonstrate its capabilities on a real-world example. Second, we developed an agentic AI solution for the document retrieval task in the context of software engineering documents. Our solution enables performing various use cases on a body of documents related to the development of a single software, including search, question answering, tracking changes, and large document summarization. In this case, each use case is handled by a dedicated LLM-based agent, which performs all subtasks related to the corresponding use case. We conclude by hinting at the future perspectives of our line of research.
Robots are finding wider adoption in human environments, increasing the need for natural human-robot interaction. However, understanding a natural language command requires the robot to infer the intended task and how to decompose it into executable actions, and to ground those actions in the robot's knowledge of the environment, including relevant objects, agents, and locations. This challenge can be addressed by combining the capabilities of Large language models (LLMs) to understand natural language with 3D scene graphs (3DSGs) for grounding inferred actions in a semantic representation of the environment. However, many 3DSGs lack explicit spatial relations between objects, even though humans often rely on these relations to describe an environment. This paper investigates whether incorporating open- or closed-vocabulary spatial relations into 3DSGs can improve the ability of LLMs to interpret natural language commands. To address this, we propose an LLM-based pipeline for target object grounding from open-vocabulary language commands and a vision language model (VLM)-based pipeline to add open-vocabulary spatial edges to 3DSGs from images captured while mapping. Finally, two LLMs are evaluated in a study assessing their performance on the downstream task of target object grounding. Our study demonstrates that explicit spatial relations improve the ability of LLMs to ground objects. Moreover, open-vocabulary relation generation with VLMs proves feasible from robot-captured images, but their advantage over closed-vocabulary relations is found to be limited.
Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts from individual competence to organizational capability. In this work, we explore a complementary dimension of width scaling with multi-agent systems to address broad information seeking. Existing multi-agent systems often rely on hand-crafted workflows and turn-taking interactions that fail to parallelize work effectively. To bridge this gap, we propose WideSeek-R1, a lead-agent-subagent framework trained via multi-agent reinforcement learning (MARL) to synergize scalable orchestration and parallel execution. By utilizing a shared LLM with isolated contexts and specialized tools, WideSeek-R1 jointly optimizes the lead agent and parallel subagents on a curated dataset of 20k broad information-seeking tasks. Extensive experiments show that WideSeek-R1-4B achieves an item F1 score of 40.0% on the WideSearch benchmark, which is comparable to the performance of single-agent DeepSeek-R1-671B. Furthermore, WideSeek-R1-4B exhibits consistent performance gains as the number of parallel subagents increases, highlighting the effectiveness of width scaling.
Organic solar cells (OSCs) hold great promise for sustainable energy, but discovering high-performance materials is time-consuming and costly. Existing molecular generation methods can aid the design of OSC molecules, but they are mostly confined to optimizing known backbones and lack effective use of domain-specific chemical knowledge, often leading to unrealistic candidates. In this paper, we introduce OSCAgent, a multi-agent framework for OSC molecular discovery that unifies retrieval-augmented design, molecular generation, and systematic evaluation into a continuously improving pipeline, without requiring additional human intervention. OSCAgent comprises three collaborative agents. The Planner retrieves knowledge from literature-curated molecules and prior candidates to guide design directions. The Generator proposes new OSC acceptors aligned with these plans. The Experimenter performs comprehensive evaluation of candidate molecules and provides feedback for refinement. Experiments show that OSCAgent produces chemically valid, synthetically accessible OSC molecules and achieves superior predicted performance compared to both traditional and large language model (LLM)-only baselines. Representative results demonstrate that some candidates achieve predicted efficiencies approaching 18\%. The code will be publicly available.
Large language models (LLMs) are being integrated into socially assistive robots (SARs) and other conversational agents providing mental health and well-being support. These agents are often designed to sound empathic and supportive in order to maximize user's engagement, yet it remains unclear how increasing the level of supportive framing in system prompts influences safety relevant behavior. We evaluated 6 LLMs across 3 system prompts with varying levels of supportiveness on 80 synthetic queries spanning 4 well-being domains (1440 responses). An LLM judge framework, validated against human ratings, assessed safety and care quality. Moderately supportive prompts improved empathy and constructive support while maintaining safety. In contrast, strongly validating prompts significantly degraded safety and, in some cases, care across all domains, with substantial variation across models. We discuss implications for prompt design, model selection, and domain specific safeguards in SARs deployment.
Proactive agents that anticipate user intentions without explicit prompts represent a significant evolution in human-AI interaction, promising to reduce cognitive load and streamline workflows. However, existing datasets suffer from two critical deficiencies: (1) reliance on LLM-synthesized data that fails to capture authentic human decision-making patterns, and (2) focus on isolated tasks rather than continuous workflows, missing the pre-assistance behavioral context essential for learning proactive intervention signals. To address these gaps, we introduce ProAgentBench, a rigorous benchmark for proactive agents in working scenarios. Our contributions include: (1) a hierarchical task framework that decomposes proactive assistance into timing prediction and assist content generation; (2) a privacy-compliant dataset with 28,000+ events from 500+ hours of real user sessions, preserving bursty interaction patterns (burstiness B=0.787) absent in synthetic data; and (3) extensive experiments that evaluates LLM- and VLM-based baselines. Numerically, we showed that long-term memory and historical context significantly enhance prediction accuracy, while real-world training data substantially outperforms synthetic alternatives. We release our dataset and code at https://anonymous.4open.science/r/ProAgentBench-6BC0.
Social robots and conversational agents are being explored as supports for wellbeing, goal-setting, and everyday self-regulation. While prior work highlights their potential to motivate and guide users, much of the evidence relies on self-reported outcomes or short, researcher-mediated encounters. As a result, we know little about the interaction dynamics that unfold when people use such systems in real-world contexts, and how these dynamics should shape future robot wellbeing coaches. This paper addresses this gap through content analysis of 4352 messages exchanged longitudinally between 38 university students and an LLM-based wellbeing coach. Our results provide a fine-grained view into how users naturally shape, steer, and sometimes struggle within supportive human-AI dialogue, revealing patterns of user-led direction, guidance-seeking, and emotional expression. We discuss how these dynamics can inform the design of robot wellbeing coaches that support user autonomy, provide appropriate scaffolding, and uphold ethical boundaries in sustained wellbeing interactions.
The rapid progress in Automated Program Repair (APR) has been fueled by advances in AI, particularly large language models (LLMs) and agent-based systems. SWE-Bench is a benchmark designed to evaluate repair systems using real issues mined from popular open-source Python repositories. Its public leaderboards-SWE-Bench Lite and Verified-have become central platforms for tracking progress and comparing solutions. In this paper, we present the first comprehensive study of these two leaderboards, examining who is submitting solutions, the products behind the submissions, the LLMs employed, and the openness of the approaches. We analyze 79 entries submitted to Lite leaderboard and 133 to Verified. Our results show that most entries on both leaderboards originate from industry, particularly small companies and large publicly traded companies. These submissions often achieve top results, although academic contributions-typically open source-also remain competitive. We also find a clear dominance of proprietary LLMs, especially Claude family, with state-of-the-art results on both leaderboards currently achieved by Claude 4 Sonnet. These findings offer insights into the SWE-Bench ecosystem that can guide greater transparency and diversity in future benchmark-driven research.
Architecture Knowledge Management (AKM) is crucial for maintaining current and comprehensive software Architecture Knowledge (AK) in a software project. However AKM is often a laborious process and is not adopted by developers and architects. While LLMs present an opportunity for automation, a naive, single-prompt approach is often ineffective, constrained by context limits and an inability to grasp the distributed nature of architectural knowledge. To address these limitations, we propose an Agentic approach for AKM, AgenticAKM, where the complex problem of architecture recovery and documentation is decomposed into manageable sub-tasks. Specialized agents for architecture Extraction, Retrieval, Generation, and Validation collaborate in a structured workflow to generate AK. To validate we made an initial instantiation of our approach to generate Architecture Decision Records (ADRs) from code repositories. We validated our approach through a user study with 29 repositories. The results demonstrate that our agentic approach generates better ADRs, and is a promising and practical approach for automating AKM.
LLM-based multi-agent systems have demonstrated impressive capabilities, but they also introduce significant safety risks when individual agents fail or behave adversarially. In this work, we study the automated design of agentic systems that remain safe even when a subset of agents is compromised. We formalize this challenge as a Stackelberg security game between a system designer (the Meta-Agent) and a best-responding Meta-Adversary that selects and compromises a subset of agents to minimize safety. We propose Meta-Adversary-Meta-Agent (MaMa), a novel algorithm for approximately solving this game and automatically designing safe agentic systems. Our approach uses LLM-based adversarial search, where the Meta-Agent iteratively proposes system designs and receives feedback based on the strongest attacks discovered by the Meta-Adversary. Empirical evaluations across diverse environments show that systems designed with MaMa consistently defend against worst-case attacks while maintaining performance comparable to systems optimized solely for task success. Moreover, the resulting systems generalize to stronger adversaries, as well as ones with different attack objectives or underlying LLMs, demonstrating robust safety beyond the training setting.
Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to acquire increasingly complex reasoning and agentic behaviors. In this work, we propose two simple techniques to improve policy gradient algorithms for LLMs. First, we replace the fixed anchor policy during RL with an Exponential Moving Average (EMA), similar to a target network in deep Q-learning. Second, we introduce Top-k KL estimator, which allows for flexible interpolation between exact KL and sampled KL. We derive the stability conditions for using EMA anchor; moreover, we show that our Top-k KL estimator yields both unbiased KL values and unbiased gradients at any k, while bringing the benefits of exact KL. When combined with GRPO, the two techniques (EMA-PG) lead to a significant performance boost. On math reasoning, it allows R1-distilled Qwen-1.5B to reach 53.9% on OlympiadBench compared to 50.8% by GRPO. On agentic RL domains, with Qwen-3B base, EMA-PG improves GRPO by an average of 33.3% across 7 datasets of Q&A with search engines, including 29.7% $\rightarrow$ 44.1% on HotpotQA, 27.4% $\rightarrow$ 40.1% on 2WikiMultiHopQA. Overall, we show that EMA-PG is a simple, principled, and powerful approach to scaling RL for LLMs. Code: https://github.com/LunjunZhang/ema-pg
Embodied agents operating in multi-agent, partially observable, and decentralized environments must plan and act despite pervasive uncertainty about hidden objects and collaborators' intentions. Recent advances in applying Large Language Models (LLMs) to embodied agents have addressed many long-standing challenges, such as high-level goal decomposition and online adaptation. Yet, uncertainty is still primarily mitigated through frequent inter-agent communication. This incurs substantial token and time costs, and can disrupt established workflows, when human partners are involved. We introduce PCE, a Planner-Composer-Evaluator framework that converts the fragmented assumptions latent in LLM reasoning traces into a structured decision tree. Internal nodes encode environment assumptions and leaves map to actions; each path is then scored by scenario likelihood, goal-directed gain, and execution cost to guide rational action selection without heavy communication. Across two challenging multi-agent benchmarks (C-WAH and TDW-MAT) and three diverse LLM backbones, PCE consistently outperforms communication-centric baselines in success rate and task efficiency while showing comparable token usage. Ablation results indicate that the performance gains obtained by scaling model capacity or reasoning depth persist even when PCE is applied, while PCE consistently raises the baseline across both capacity and reasoning-depth scales, confirming that structured uncertainty handling complements both forms of scaling. A user study further demonstrates that PCE produces communication patterns that human partners perceive as more efficient and trustworthy. Together, these results establish a principled route for turning latent LLM assumptions into reliable strategies for uncertainty-aware planning.
Large language models (LLMs) have revolutionized automated code generation, yet the evaluation of their real-world effectiveness remains limited by static benchmarks and simplistic metrics. We present ProxyWar, a novel framework that systematically assesses code generation quality by embedding LLM-generated agents within diverse, competitive game environments. Unlike existing approaches, ProxyWar evaluates not only functional correctness but also the operational characteristics of generated programs, combining automated testing, iterative code repair, and multi-agent tournaments to provide a holistic view of program behavior. Applied to a range of state-of-the-art coders and games, our approach uncovers notable discrepancies between benchmark scores and actual performance in dynamic settings, revealing overlooked limitations and opportunities for improvement. These findings highlight the need for richer, competition-based evaluation of code generation. Looking forward, ProxyWar lays a foundation for research into LLM-driven algorithm discovery, adaptive problem solving, and the study of practical efficiency and robustness, including the potential for models to outperform hand-crafted agents. The project is available at https://github.com/xinke-wang/ProxyWar.
Managing agent thought and observation during multi-turn agent-environment interactions is an emerging strategy to improve agent efficiency. However, existing studies treat the entire interaction trajectories equally, overlooking the thought necessity and observation utility varies across turns. To this end, we first conduct quantitative investigations into how thought and observation affect agent effectiveness and efficiency. Based on our findings, we propose Agent-Omit, a unified training framework that empowers LLM agents to adaptively omit redundant thoughts and observations. Specifically, we first synthesize a small amount of cold-start data, including both single-turn and multi-turn omission scenarios, to fine-tune the agent for omission behaviors. Furthermore, we introduce an omit-aware agentic reinforcement learning approach, incorporating a dual sampling mechanism and a tailored omission reward to incentivize the agent's adaptive omission capability. Theoretically, we prove that the deviation of our omission policy is upper-bounded by KL-divergence. Experimental results on five agent benchmarks show that our constructed Agent-Omit-8B could obtain performance comparable to seven frontier LLM agent, and achieve the best effectiveness-efficiency trade-off than seven efficient LLM agents methods. Our code and data are available at https://github.com/usail-hkust/Agent-Omit.
Data agents are an emerging paradigm that leverages large language models (LLMs) and tool-using agents to automate data management, preparation, and analysis tasks. However, the term "data agent" is currently used inconsistently, conflating simple query responsive assistants with aspirational fully autonomous "data scientists". This ambiguity blurs capability boundaries and accountability, making it difficult for users, system builders, and regulators to reason about what a "data agent" can and cannot do. In this tutorial, we propose the first hierarchical taxonomy of data agents from Level 0 (L0, no autonomy) to Level 5 (L5, full autonomy). Building on this taxonomy, we will introduce a lifecycleand level-driven view of data agents. We will (1) present the L0-L5 taxonomy and the key evolutionary leaps that separate simple assistants from truly autonomous data agents, (2) review representative L0-L2 systems across data management, preparation, and analysis, (3) highlight emerging Proto-L3 systems that strive to autonomously orchestrate end-to-end data workflows to tackle diverse and comprehensive data-related tasks under supervision, and (4) discuss forward-looking research challenges towards proactive (L4) and generative (L5) data agents. We aim to offer both a practical map of today's systems and a research roadmap for the next decade of data-agent development.
Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult test case generation or inefficient random input sampling. To address this limitation, we propose Agentic Verifier, an execution-based agent that actively reasons about program behaviors and searches for highly discriminative test inputs that expose behavioral discrepancies among candidate solutions. Through multi-turn interaction with code execution environments, the verifier iteratively refines the candidate input generator and produces targeted counterexamples rather than blindly sampling inputs. We train the verifier to acquire this discriminative input generation capability via a scalable pipeline combining large-scale data synthesis, rejection fine-tuning, and agentic reinforcement learning. Extensive experiments across five competitive programming benchmarks demonstrate consistent improvements over strong execution-based baselines, achieving up to +10-15% absolute gains in Best@K accuracy. Further analysis reveals clear test-time scaling behavior and highlights the verifier's broader potential beyond reranking.
Inference-time scaling strategies, particularly Monte Carlo Tree Search (MCTS), have significantly enhanced the reasoning capabilities of Large Language Models (LLMs). However, current approaches remain predominantly stateless, discarding successful reasoning patterns after each problem instance and failing to mimic the empirical accumulation of wisdom characteristic of human problem-solving. To bridge this gap, we introduce Empirical-MCTS, a dual-loop framework that transforms stateless search into a continuous, non-parametric learning process. The framework unifies local exploration with global memory optimization through two novel mechanisms: Pairwise-Experience-Evolutionary Meta-Prompting (PE-EMP) and a Memory Optimization Agent. PE-EMP functions as a reflexive optimizer within the local search, utilizing pairwise feedback to dynamically synthesize adaptive criteria and evolve meta-prompts (system prompts) in real-time. Simultaneously, the Memory Optimization Agent manages a global repository as a dynamic policy prior, employing atomic operations to distill high-quality insights across problems. Extensive evaluations on complex reasoning benchmarks, including AIME25, ARC-AGI-2, and MathArena Apex, demonstrate that Empirical-MCTS significantly outperforms both stateless MCTS strategies and standalone experience-driven agents. These results underscore the critical necessity of coupling structured search with empirical accumulation for mastering complex, open-ended reasoning tasks.
Multi-agent systems (MAS) have emerged as a prominent paradigm for leveraging large language models (LLMs) to tackle complex tasks. However, the mechanisms governing the effectiveness of MAS built upon publicly available LLMs, specifically the underlying rationales for their success or failure, remain largely unexplored. In this paper, we revisit MAS through the perspective of uncertainty, considering both intra- and inter-agent dynamics by investigating entropy transitions during problem-solving across various topologies and six benchmark tasks. By analyzing 245 features spanning token-, trajectory-, and round-level entropy, we counterintuitively find that a single agent outperforms MAS in approximately 43.3% of cases, and that uncertainty dynamics are largely determined during the first round of interaction. Furthermore, we provide three key observations: 1) Certainty Preference: reducing uncertainty at any stage for any agent is critical for guaranteeing correct solutions; 2) Base Uncertainty: base models with lower entropy during problem-solving directly benefit MAS performance; and 3) Task Awareness: entropy dynamics of MAS play varying roles across different tasks. Building on these insights, we introduce a simple yet effective algorithm, the Entropy Judger, to select solutions from MAS's pass@k results, leading to consistent accuracy improvements across all MAS configurations and tasks. Our source code is available at https://github.com/AgenticFinLab/multiagent-entropy.
The enhanced capabilities of LLM-based agents come with an emergency for model planning and tool-use abilities. Attributing to helpful-harmless trade-off from LLM alignment, agents typically also inherit the flaw of "over-refusal", which is a passive failure mode. However, the proactive planning and action capabilities of agents introduce another crucial danger on the other side of the trade-off. This phenomenon we term "Toxic Proactivity'': an active failure mode in which an agent, driven by the optimization for Machiavellian helpfulness, disregards ethical constraints to maximize utility. Unlike over-refusal, Toxic Proactivity manifests as the agent taking excessive or manipulative measures to ensure its "usefulness'' is maintained. Existing research pays little attention to identifying this behavior, as it often lacks the subtle context required for such strategies to unfold. To reveal this risk, we introduce a novel evaluation framework based on dilemma-driven interactions between dual models, enabling the simulation and analysis of agent behavior over multi-step behavioral trajectories. Through extensive experiments with mainstream LLMs, we demonstrate that Toxic Proactivity is a widespread behavioral phenomenon and reveal two major tendencies. We further present a systematic benchmark for evaluating Toxic Proactive behavior across contextual settings.
Heterogeneous multi-robot systems are increasingly deployed in long-horizon missions that require coordination among robots with diverse capabilities. However, existing planning approaches struggle to construct accurate symbolic representations and maintain plan consistency in dynamic environments. Classical PDDL planners require manually crafted symbolic models, while LLM-based planners often ignore agent heterogeneity and environmental uncertainty. We introduce KGLAMP, a knowledge-graph-guided LLM planning framework for heterogeneous multi-robot teams. The framework maintains a structured knowledge graph encoding object relations, spatial reachability, and robot capabilities, which guides the LLM in generating accurate PDDL problem specifications. The knowledge graph serves as a persistent, dynamically updated memory that incorporates new observations and triggers replanning upon detecting inconsistencies, enabling symbolic plans to adapt to evolving world states. Experiments on the MAT-THOR benchmark show that KGLAMP improves performance by at least 25.5% over both LLM-only and PDDL-based variants.
Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture information distributed across thousands of frames. Existing approaches either sample frames uniformly (risking information loss) or select keyframes in a single pass (with no recovery from poor choices). We propose VideoBrain, an end-to-end framework that enables VLMs to adaptively acquire visual information through learned sampling policies. Our approach features dual complementary agents: a CLIP-based agent for semantic retrieval across the video and a Uniform agent for dense temporal sampling within intervals. Unlike prior agent-based methods that rely on text-only LLMs orchestrating visual tools, our VLM directly perceives frames and reasons about information sufficiency. To prevent models from invoking agents indiscriminately to maximize rewards, we introduce a behavior-aware reward function coupled with a data classification pipeline that teaches the model when agent invocation is genuinely beneficial. Experiments on four long video benchmarks demonstrate that VideoBrain achieves +3.5% to +9.0% improvement over the baseline while using 30-40% fewer frames, with strong cross-dataset generalization to short video benchmarks.
Large language models (LLMs) achieve strong performance when all task-relevant information is available upfront, as in static prediction and instruction-following problems. However, many real-world decision-making tasks are inherently online: crucial information must be acquired through interaction, feedback is delayed, and effective behavior requires balancing information collection and exploitation over time. While in-context learning enables adaptation without weight updates, existing LLMs often struggle to reliably leverage in-context interaction experience in such settings. In this work, we show that this limitation can be addressed through training. We introduce ORBIT, a multi-task, multi-episode meta-reinforcement learning framework that trains LLMs to learn from interaction in context. After meta-training, a relatively small open-source model (Qwen3-14B) demonstrates substantially improved in-context online learning on entirely unseen environments, matching the performance of GPT-5.2 and outperforming standard RL fine-tuning by a large margin. Scaling experiments further reveal consistent gains with model size, suggesting significant headroom for learn-at-inference-time decision-making agents. Code reproducing the results in the paper can be found at https://github.com/XiaofengLin7/ORBIT.
Millions of children worldwide are affected by severe rare Mendelian disorders, yet exome and genome sequencing still fail to provide a definitive molecular diagnosis for a large fraction of patients, prolonging the diagnostic odyssey. Bridging this gap increasingly requires transitioning from DNA-only interpretation to multi-modal diagnostic reasoning that combines genomic data, transcriptomic sequencing (RNA-seq), and phenotype information; however, computational frameworks that coherently integrate these signals remain limited. Here we present RareCollab, an agentic diagnostic framework that pairs a stable quantitative Diagnostic Engine with Large Language Model (LLM)-based specialist modules that produce high-resolution, interpretable assessments from transcriptomic signals, phenotypes, variant databases, and the literature to prioritize potential diagnostic variants. In a rigorously curated benchmark of Undiagnosed Diseases Network (UDN) patients with paired genomic and transcriptomic data, RareCollab achieved 77% top-5 diagnostic accuracy and improved top-1 to top-5 accuracy by ~20% over widely used variant-prioritization approaches. RareCollab illustrates how modular artificial intelligence (AI) can operationalize multi-modal evidence for accurate, scalable rare disease diagnosis, offering a promising path toward reducing the diagnostic odyssey for affected families.
Planning in interactive environments is challenging under partial observability: task-critical preconditions (e.g., object locations or container states) may be unknown at decision time, yet grounding them through interaction is costly. Learned world models can cheaply predict missing facts, but prediction errors can silently induce infeasible commitments. We present \textbf{Active Epistemic Control (AEC)}, an epistemic-categorical planning layer that integrates model-based belief management with categorical feasibility checks. AEC maintains a strict separation between a \emph{grounded fact store} used for commitment and a \emph{belief store} used only for pruning candidate plans. At each step, it either queries the environment to ground an unresolved predicate when uncertainty is high or predictions are ambiguous, or simulates the predicate to filter hypotheses when confidence is sufficient. Final commitment is gated by grounded precondition coverage and an SQ-BCP pullback-style compatibility check, so simulated beliefs affect efficiency but cannot directly certify feasibility. Experiments on ALFWorld and ScienceWorld show that AEC achieves competitive success with fewer replanning rounds than strong LLM-agent baselines.
While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limited by their high computational cost and error propagation. This paper proposes AgentArk, a novel framework to distill multi-agent dynamics into the weights of a single model, effectively transforming explicit test-time interactions into implicit model capabilities. This equips a single agent with the intelligence of multi-agent systems while remaining computationally efficient. Specifically, we investigate three hierarchical distillation strategies across various models, tasks, scaling, and scenarios: reasoning-enhanced fine-tuning; trajectory-based augmentation; and process-aware distillation. By shifting the burden of computation from inference to training, the distilled models preserve the efficiency of one agent while exhibiting strong reasoning and self-correction performance of multiple agents. They further demonstrate enhanced robustness and generalization across diverse reasoning tasks. We hope this work can shed light on future research on efficient and robust multi-agent development. Our code is at https://github.com/AIFrontierLab/AgentArk.
Mathematical problem solving is a fundamental benchmark for assessing the reasoning capabilities of artificial intelligence and a gateway to applications in education, science, and engineering where reliable symbolic reasoning is essential. Although recent advances in multi-agent LLM-based systems have enhanced their mathematical reasoning capabilities, they still lack a reliably revisable representation of the reasoning process. Existing agents either operate in rigid sequential pipelines that cannot correct earlier steps or rely on heuristic self-evaluation that can fail to identify and fix errors. In addition, programmatic context can distract language models and degrade accuracy. To address these gaps, we introduce Iteratively Improved Program Construction (IIPC), a reasoning method that iteratively refines programmatic reasoning chains and combines execution feedback with the native Chain-of-thought abilities of the base LLM to maintain high-level contextual focus. IIPC surpasses competing approaches in the majority of reasoning benchmarks on multiple base LLMs. All code and implementations are released as open source.
Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to only generate frontend web pages, masking the lack of real full-stack data processing and storage with fancy visual effects. Notably, constructing production-level full-stack web applications is far more challenging than only generating frontend web pages, demanding careful control of data flow, comprehensive understanding of constantly updating packages and dependencies, and accurate localization of obscure bugs in the codebase. To address these difficulties, we introduce FullStack-Agent, a unified agent system for full-stack agentic coding that consists of three parts: (1) FullStack-Dev, a multi-agent framework with strong planning, code editing, codebase navigation, and bug localization abilities. (2) FullStack-Learn, an innovative data-scaling and self-improving method that back-translates crawled and synthesized website repositories to improve the backbone LLM of FullStack-Dev. (3) FullStack-Bench, a comprehensive benchmark that systematically tests the frontend, backend and database functionalities of the generated website. Our FullStack-Dev outperforms the previous state-of-the-art method by 8.7%, 38.2%, and 15.9% on the frontend, backend, and database test cases respectively. Additionally, FullStack-Learn raises the performance of a 30B model by 9.7%, 9.5%, and 2.8% on the three sets of test cases through self-improvement, demonstrating the effectiveness of our approach. The code is released at https://github.com/mnluzimu/FullStack-Agent.
LLM-based multi-agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance by increasing the number of agents; however, we find that such scaling exhibits strong diminishing returns in homogeneous settings, while introducing heterogeneity (e.g., different models, prompts, or tools) continues to yield substantial gains. This raises a fundamental question: what limits scaling, and why does diversity help? We present an information-theoretic framework showing that MAS performance is bounded by the intrinsic task uncertainty, not by agent count. We derive architecture-agnostic bounds demonstrating that improvements depend on how many effective channels the system accesses. Homogeneous agents saturate early because their outputs are strongly correlated, whereas heterogeneous agents contribute complementary evidence. We further introduce $K^*$, an effective channel count that quantifies the number of effective channels without ground-truth labels. Empirically, we show that heterogeneous configurations consistently outperform homogeneous scaling: 2 diverse agents can match or exceed the performance of 16 homogeneous agents. Our results provide principled guidelines for building efficient and robust MAS through diversity-aware design. Code and Dataset are available at the link: https://github.com/SafeRL-Lab/Agent-Scaling.
While Open Set Semantic Mapping and 3D Semantic Scene Graphs (3DSSGs) are established paradigms in robotic perception, deploying them effectively to support high-level reasoning in large-scale, real-world environments remains a significant challenge. Most existing approaches decouple perception from representation, treating the scene graph as a derivative layer generated post hoc. This limits both consistency and scalability. In contrast, we propose a mapping architecture where the 3DSSG serves as the foundational backend, acting as the primary knowledge representation for the entire mapping process. Our approach leverages prior work on incremental scene graph prediction to infer and update the graph structure in real-time as the environment is explored. This ensures that the map remains topologically consistent and computationally efficient, even during extended operations in large-scale settings. By maintaining an explicit, spatially grounded representation that supports both flat and hierarchical topologies, we bridge the gap between sub-symbolic raw sensor data and high-level symbolic reasoning. Consequently, this provides a stable, verifiable structure that knowledge-driven frameworks, ranging from knowledge graphs and ontologies to Large Language Models (LLMs), can directly exploit, enabling agents to operate with enhanced interpretability, trustworthiness, and alignment to human concepts.