每天知道
你的领域
出了什么

Disease severity classification for genetic conditions is subjective and labor-intensive, creating bottlenecks in genomic screening, where commercial panels vary widely in size and overlap. We developed an autonomous AI agent integrating Reasoning and Acting (ReAct) with Retrieval-Augmented Generation (RAG) to classify 10,211 Human Phenotype Ontology terms. It uses American College of Medical Genetics (ACMG)-endorsed severity guidelines and American College of Obstetricians and Gynecologists (ACOG) quality-of-life criteria to retrieve PubMed literature, generate interpretable reasoning chains, and independently verify claims. At the phenotype level, using expert-curated cohorts, the agent achieved 93.55% accuracy (MCC 0.9237) with 82.6% to 91.4% of claims supported by direct evidence or valid inferences. Gene-level severity was aggregated across 8,738 pairs, identifying 3,283 autosomal recessive pairs with severe or profound presentations. External validation showed 95.2% concordance with Mackenzie's Mission gene list. This system enables standardized panel design by providing reliable, automated classification supported by direct evidence.

Retrieval-Augmented Generation (RAG) is increasingly used to ground large language model (LLM) outputs in scientific literature. However, in open-ended literature exploration, the evidence context used for generation is often produced through hidden retrieval, reranking, assessment, and filtering steps. Users may receive retrieval summaries without knowing how the system constructed the evidence context, which evidence units were retained or discarded, or whether potentially useful evidence was excluded before synthesis. We present FootprintRAG, an LLM-agent-powered visual analytics system for evidence context refinement in RAG-based scientific literature exploration. The core idea is to treat the RAG evidence context as an explicit, inspectable, and revisable analytical object before generation. FootprintRAG parses scientific literature into text and figure evidence units, expands an initial query into parallel query variants, retrieves and assesses evidence across iterative rounds, and surfaces ERS-ranked supplementary candidates from the corpus-level evidence space. Through coordinated views, the system connects retrieval trajectories, evidence-state revision, and provenance-aware summary generation into a user-steerable workflow. We evaluate FootprintRAG through two case studies, a user study, and a workflow-level comparison with representative RAG systems. The results show that FootprintRAG helps users compare retrieval directions, revise candidate evidence, recover potentially overlooked evidence, and trace generated summaries back to supporting evidence units. FootprintRAG is available at https://github.com/meteorshowering/FootprintRAGVA.git.

Tool learning enables large language models (LLMs) to use external tools for tasks beyond parametric knowledge. Reinforcement learning can optimize tool-call behavior from feedback, but current methods still face two problems: fixed-threshold curricula can become misaligned with the policy's evolving capability boundary, and additive rewards can leak argument-level credit when the predicted tool is wrong. To address these problems, we propose MATCH, a closed-loop framework for model-aware tool learning with curriculum scheduling and hierarchically gated rewards. Model-Aware Curriculum Learning (MACL) maintains reward-derived sample difficulty that co-evolves with the policy, and each epoch selects samples near the current capability boundary together with a top-k pool of harder cases. Hierarchical Tool-call Gated Reward (HTGR) scores tool name, argument key, and argument value as a gated chain, granting credit at each level only when prerequisites hold. The same HTGR rewards drive both GRPO updates and MACL's difficulty refresh, closing the loop between policy optimization and sample scheduling. On API-Bank and BFCL V3, MATCH reaches 72.19% and 62.87% overall accuracy, outperforming the main supervised and RL-based baselines. Backbone experiments further show consistent improvements across four backbones from two model families.

Self-evolving methods reduce the need for human-annotated trajectories by allowing tool-using agents to generate their own training data. Yet existing methods typically separate trajectory generation from evaluation, relying on static verifiers that cannot adapt to emerging failure modes or self-consistency signals that may reinforce errors shared across trajectories. Jointly adapting planning, execution, and evaluation offers a promising alternative, but introduces a fundamental coordination challenge: each component continuously changes the data or feedback used to train the others. We address this challenge with UnifiedPlayers, a cooperative framework comprising a Planning Player that generates tasks, an Execution Player that produces multi-turn trajectories with Python tool calls, and an Evaluation Player that constructs executable verifiers. We design role-specific rewards that coordinate the three players toward a shared learning objective under GRPO. Across two model backbones and twelve reasoning benchmarks, UnifiedPlayers outperforms the strongest prior baseline by at least 3.5% on mathematical reasoning and 3.9% on general reasoning tasks. Moreover, the learned verifier achieves 84.2% adversarial detection accuracy, while its reward signal exhibits 2.03$\times$ higher per-question variance than a self-consistency baseline, providing more discriminative verifications. These results highlight cooperation among specialized players as a promising path toward self-enhanced tool-integrated agents.

Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots without robot-specific training.Whether this paradigm is also safe, however, has not been asked. We evaluate coding agent under a safety constraint, where each task pairs a manipulation goal with an obstacle the robot must not touch. The agent pursues the goal but collides with the obstacle in most cases, treating task completion as its sole objective while neglecting safety. The agent reasons about the obstacle in its traces, and the prompt already forbids touching it, so neither perception nor instruction is at fault; the fault lies in the planning, where the stated constraint never becomes a priority. By decomposing manipulation into a route phase and a contact-rich moment, we locate the source of the failure. Along the route, the model cannot prioritize the safety constraint, having no notion of a clearing route and none of replanning once a chosen route becomes infeasible. At the contact, it is unaware that contact execution is bounded by the same constraint. To close this gap, we present SafeHarness, which equips the model with two obstacle-aware harnesses that enable it to prioritize the safety constraint. Obstacle-aware route planning grounds the objects as bounding boxes and draws candidate routes over them as sequences of waypoints. The agent then plans a route in advance, verifies it, replans when necessary, and only then executes it. Obstacle-aware contact execution instead selects the contact position so that the contact itself avoids the obstacle. SafeHarness attains 71.9% task success and 87.5% collision avoidance, surpassing the previous SOTA by 6.5% and 27.0%, respectively. These results are $2.3\times$ and $1.5\times$ those of the same agent without harnesses.

Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. Because retrieval relies on an index that represents each document through index keys, retrieval quality depends heavily on how effectively these keys expose the knowledge contained in each document. However, effective index representations vary across retrieval environments, making it difficult for any fixed optimization strategy to perform consistently. Yet evolving an index to its retrieval environment remains largely human-driven, requiring humans to diagnose retrieval failures, refine the optimization strategy, and reprocess the index accordingly. We propose SELF-INDEX, a framework that enables an index to self-evolve without human intervention. Its Optimizer autonomously diagnoses retrieval shortfalls, selectively revises the responsible index keys, and validates each revision before updating the index. Beyond reacting to observed retrieval demands, SELF-INDEX proactively explores additional demands through a Query Simulator, allowing the index to evolve beyond the queries already available for optimization. Across diverse corpora and retrievers, SELF-INDEX consistently improves retrieval performance while outperforming existing index optimization methods. We further show that these benefits extend to downstream applications, improving the effectiveness and efficiency of search agents and helping agent memory systems retrieve useful past interactions.

Root-cause analysis (RCA) is a critical yet labor-intensive task for maintaining modern microservice systems, making it an attractive target for large language models (LLMs). Recent agentic approaches allow an LLM to iteratively explore raw telemetry by generating and executing code, asking a single model to simultaneously retrieve evidence, localize faults, and infer root causes over large volumes of heterogeneous telemetry, which leads to high computational cost, unstable behavior, and limited diagnostic accuracy. However, raw telemetry consists of numeric metrics, structured traces, and machine-generated logs that are not directly suitable for LLM processing. We present EviRCA, a framework for LLM-based RCA that decouples deterministic evidence extraction from LLM reasoning. A system-agnostic extraction stage converts raw metrics, traces, and logs into a compact set of faithful multimodal evidence cards, while the LLM reasons only over these structured observations through a small set of predefined read-only tools, without accessing raw telemetry or executing code. We evaluate EviRCA on OpenRCA, a benchmark built from real, heterogeneous telemetry across three enterprise systems. EviRCA achieves a correct rate of 40.6%-43.9% across two different LLMs, substantially outperforming prior OpenRCA baselines that achieve up to 15.2%, while reducing token consumption by 15-26x and execution time by 3-20x. Moreover, EviRCA solves hard cases requiring simultaneous reasoning over time, components, and root causes, a setting where previous approaches reported near-zero performance. Our process-level failure analysis further shows that the bottleneck lies in judging the evidence that the extraction stage has already surfaced, rather than searching for it, suggesting that the effectiveness of LLM-based RCA depends heavily on the quality of evidence extraction.

Materials discovery and design campaigns can be formulated as constrained multi-objective Bayesian optimization (CMOBO) problems, within which each experimental decision negotiates between two coupled but competing goals: discovering feasible candidates and refining the underlying Pareto front. Here we recast acquisition-function choice as an adaptive policy-selection problem over a portfolio of conventional and feasibility-focused acquisition functions. This was done using two controllers: UCB-Bandit, a modified UCB multi-armed bandit, and Agentic-Switch, a multi-agent decision system driven by a large language model (LLM). Both were evaluated against fixed-policy baselines in silico across five synthetic benchmark functions and two materials design case studies. The adaptive policies performed competitively in terms of both cumulative feasibility count and feasible hypervolume improvement, while each individual acquisition function performed well for only one metric, suggesting that adaptive policies are better suited for constrained materials science problems.

Reinforcement learning for LLM agents involves two distinct optimization di- mensions: how environment feedback is exploited within a trajectory, and how complete trajectories are aggregated across a batch. We formulate these dimen- sions as Intra-Trajectory Feedback Attribution and Inter-Trajectory Objec- tive Aggregation, and introduce BATON (Bayesian Attribution and Trajectory Objective Normalization), a dual-axis policy optimization framework. BATON instantiates the first axis with Bayesian Feedback Attribution, which constructs a feedback-conditioned posterior over sampled actions, and the second with Trajec- tory Mass Normalization (TMN), which assigns equal optimization mass to com- plete trajectories. Experiments with GRPO and GiGPO on ALFWorld, WebShop, and SearchQA show that both axes provide independent gains and that their combi- nation consistently achieves the strongest overall performance across model scales.

Generally, most voice agents are cascaded systems, i.e., an ASR model transcribes the caller's audio, a language model reads the transcript and decides what to say and which backend tools to call, and a TTS model speaks the reply. Nearly all of the decision making happens in the language model, but existing evaluations measure it either too broadly or too narrowly. End-to-end voice benchmarks score the full pipeline, so recognition errors and model errors mix into a single number. LLM benchmarks isolate the model but they do not evaluate what makes real phone calls hard, such as transcription issues, caller's voice being split across messages and the requirement that replies follow the language and script specified. We introduce the Multi-Turn Voice Agent Benchmark (MTVA-Bench), which evaluates the language model on the same conditions it faces inside a cascaded system. The caller is played by an LLM following a set of rubrics and tool calls are answered by a mock backend which responds to the arguments the model actually sent. The benchmark contains 49 agents working across 490 reviewed scenarios and supports 7 languages. Scoring is a combination of deterministic checks on tool calls with two LLM judges, one that scores scenario specific rules and one that grades conversation quality without access to the task. Both judges must cite specific messages from the transcript. Task and conversation scores are weighted equally, since a call can complete its task and still go badly for the caller. In a seven-model study, six of the models select the correct tool within 6.4 points of one another, but their overall scores span 24.4 points. Most of the gap comes from argument values, action ordering, rule compliance, and what the model says around its tool calls.

Scientific discovery is defined by the ability to identify the boundaries of existing knowledge and venture into unexplored territory. The ultimate vision for AI in science is problem-driven autonomous research: given a fundamental challenge by a human expert, the AI independently navigates the scientific landscape, uncovers theoretical and empirical bottlenecks, and systematically expands the frontier of knowledge. In this paper, we introduce ScientistTwo, a fully autonomous multi-agent framework designed to realize this vision. Specifically, ScientistTwo takes an initial problem as input, establishes state-of-the-art baselines, formulates novel hypotheses, and coordinates specialized agents to orchestrate an end-to-end discovery cycle without human intervention. Moreover, the framework rigorously conducts experiments using diverse datasets and metrics, refines methodologies through automated ablation studies, and validates research findings via a closed-loop simulated peer-review rebuttal engine. To evaluate ScientistTwo's capabilities against the highest standards of human scientific achievement, we benchmark it across papers accepted at top-tier conferences such as ICLR, ICML, and NeurIPS. As a result, ScientistTwo autonomously generates expert-level, publishable papers and fully verified, executable codebases. Its solutions consistently outperform human state-of-the-art models, and achieve higher average review ratings than human-authored papers under automated AI review agents. These results show that ScientistTwo is not merely an assistive tool but an autonomous scientific pioneer capable of pushing the frontiers of human discovery. Project website: https://scientist-two.github.io/

Occlusion creates fundamental uncertainty in autonomous driving. Existing methods often propagate frame-wise hypotheses or optimize ego behavior against prescribed hidden-agent predictions, leaving the worst history-consistent interaction unexplored. We introduce History-Conditioned Minimax Trajectory Search (HC-MTS), which combines temporal occlusion reasoning with response-aware search. First, HC-MTS constructs finite hidden-state modes, each certified by a backward witness satisfying multi-frame visibility, occupancy, semantic-map support, and class-specific kinematic constraints. It then solves a bilevel minimax problem: an inner finite oracle maximizes the ego driving score over destination attainment and ride comfort, while the outer search selects the legal hidden-vehicle trajectory that minimizes this best-response value. Across eight Waymo Open Motion Dataset scenarios, increasing the visibility-memory horizon from K=1 to K=20 reduces the mean per-scenario vehicle, pedestrian, and total retained hidden-seed counts by 18.12%, 21.67%, and 18.45%, respectively. HC-MTS identifies six avoidable counterexamples, while no legal collision-producing attacker is found in the remaining two scenes within the finite search budget.

Travel-planning agents generate itineraries that may become infeasible after acceptance because of flight cancellations, hotel unavailability, or attraction closures. Revising these itineraries involves full replanning, classical plan repair, and LLM-based travel-agent revision, whose differing task formulations and evaluation protocols hinder comparison. We conduct a systematic empirical study using two TREK-derived benchmark sets: 500 single-disruption cases, including feasible and infeasible instances, and 200 feasible simultaneous compound-disruption cases. We compare LLM-Z3 full replanning, IPyHOPPER hierarchical repair, and an iTIMO local-revision adapter across effectiveness, plan stability, and computational cost. LLM-Z3 with Gemini achieved the highest observed compound-disruption success. IPyHOPPER nearly matched that configuration's single-disruption overall success, while preserving substantially more of the accepted itinerary on successful repairs. Successful hierarchical and local repairs made fewer edits and retained more accepted commitments than full replanning. Computational profiles differed: IPyHOPPER used no LLM inference, the evaluated LLM-Z3 adapter used compact one-call inference, and the iTIMO adapter consumed substantially more tokens. The study provides practical guidelines for balancing feasibility recovery, commitment preservation, and computational cost within evaluated settings.

Autonomous large language model (LLM) agents are moving rapidly into high-stakes domains, yet existing agentic-AI security studies remain largely domain-agnostic and overlook the distinctive, high-consequence attack surface such settings create. We examine this gap through financial trading agents, a representative case of high-stakes agentic security, where a single compromised agent has direct execution authority over real capital in an adversarial, reflexive market. To this end, we present FARSIGHT (Financial Agent Robustness and Security Investigation and Global Holistic Testing), a framework that performs scheme-level evaluation of financial LLM agents on two axes: robustness under market turbulence (including flash-crash-like scenarios), and security against three attack types: attacks on information sources, attacks on agents, and agent-as-attacker behaviors. Applying FARSIGHT to 15 representative academic schemes, we find that most overlook robustness and realistic adversarial threats: 80% fail at least one core robustness metric and 100% exhibit security vulnerabilities. These two failure modes are inseparable: a small misjudgment can cascade into a market-wide crash on its own, while an adversary can deliberately trigger the same collapse at minimal cost.

Agent harnesses supply planning guidance, organize execution, and check completion. We study how these components affect success, erroneous acceptance, and cost in two Retail experiments and an Airline pilot in $τ^2$-bench. The primary comparison pairs prewritten task-specific plans (Fixed) with shuffled policy text matched in word count (Sham), isolating the contribution of guidance content. Across 265 matched cells, Fixed improves oracle-verified success by 7.17 percentage points (90% task-clustered bootstrap interval, 1.15--13.36 points), with gains concentrated in higher-complexity tasks. A read-only terminal verifier rejects 61% of Retail oracle-invalid episodes while withholding 17% of correct ones, at less than one cent of additional cost per episode. Which component matters more depends on the loss assigned to erroneous acceptance: at low liability the planning gain dominates; at high liability the verifier's avoided false passes dominate---and a standalone verifier captures nearly all the false-pass benefit of the full planning-plus-verification stack at a fraction of its cost.

Video agents have made substantial progress in long-video understanding. Yet effective video-agent systems require costly, time-consuming manual design and trial and error. Current self-improvement methods either refine low-impact prompts, recombine predefined micro-tools, or struggle with convergence in harness optimization. To bridge this gap, we target high-impact video-tool with VideoResearcher, a training-free multi-agent framework that autonomously designs, tests, and refines tools for video understanding, like a human researcher. VideoResearcher operates through dual Solving and Evolving loops: it analyzes tool-use trajectories to identify capability gaps, coordinates specialized agents to develop and validate executable tools, and reuses evolved tools to strengthen evidence acquisition in subsequent video reasoning. Through iterative tool refinement and validation, it progressively strengthens evidence acquisition without updating model parameters. VideoResearcher achieves state-of-the-art performance among self-improving agents and approaches the human-designed upper bound, demonstrating a training-free paradigm for long-video understanding that expands agent capabilities through autonomous tool development while reducing costly manual engineering.

With the widespread industrial deployment of Large Language Models (LLMs), DeepSearch has emerged as the dominant paradigm for resolving complex user queries. It typically operates through an iterative closed-loop workflow consisting of planning and reflection, information retrieval, and answer generation. However, existing reward models (RMs) and evaluation benchmarks are primarily designed for static single-turn tasks, failing to capture the full-pipeline complexity of DeepSearch workflows. To address this limitation, we propose F2DR, a fine-grained full-pipeline DeepSearch reward framework. F2DR evaluates DeepSearch workflows across three dimensions: Content, Trajectory, and Answer, enabling comprehensive process-level assessment. We further construct DeepSearch RM-Bench, a dedicated benchmark for evaluating RMs in DeepSearch scenarios. Extensive experiments demonstrate that F2DR achieves significantly higher evaluation consistency than self-evaluation-based baselines, while DeepSearch RM-Bench exhibits strong discriminative capability across existing open-source RMs. We will publicly release the complete DeepSearch RM-Bench dataset soon.

Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the effectiveness of individual components unclear. To enable component-level comparisons, we study this question with a lightweight coding harness whose execution loop is fixed while three components are varied: planning, action space, and context management. Across four models evaluated on SWE-Bench Verified and Terminal-Bench 2.1, we evaluate 176 matched settings spanning five context-management strategies, four context-window budgets, and targeted ablations of planning and action space. We find that: (1) Context management becomes increasingly valuable as the context-window budget tightens, with most of its benefit coming from preventing context-overflow failures. (2) Staging rule-based elision before LLM-based summarization provides the strongest overall efficiency among the context-management strategies, whereas making elided content recoverable adds machinery that models rarely use and yields no accuracy gain. (3) Planning shifts from an accuracy scaffold for weaker models to a cost saver for stronger models, with little change in accuracy. (4) Predefined tools improve performance for models with weaker bash proficiency, whereas bash-capable models can operate effectively with a bash-only interface and achieve substantially lower cost, especially on command-line-centric tasks. Trajectory-level analysis explains these effects: context management extends execution trajectories without substantially altering agent behavior, planning changes where trajectories stop, and the action space changes the granularity at which code is written. These findings inform model- and budget-aware harness design and provide a modular framework for evaluating future harness components.

Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitwise reproducible, on tools that read changing state, and on a multi-step trajectory that a re-run rarely repeats. Record-and-replay makes a run reproducible, but existing agent tooling records runs only to trace or score them, not to test a code change against them. We present Chronicle, which records an agent run at its non-deterministic boundaries as immutable envelopes and replays it from the record. Its central operation, cut-point replay, serves a chosen subset of boundaries from the record and executes the complementary subset live with new code, turning a recorded incident into a regression test that runs in continuous integration. On a benchmark of 6 recorded failures with simulated model boundaries, recording adds 23 μs per crossing (0.008% of an assumed 300 ms model call), full replay issues zero model calls and is bit-stable across 20 repetitions, and cut-point tests fail on faulty code and pass on guarded and benign changes for all 6 incidents. In a mutation study of the guarded tools, cut-point tests catch every mutant that lets the recorded unsafe action through, while a baseline that stubs every boundary, using the same assertion, catches none. Chronicle and the benchmark are publicly available at https://github.com/theagentplane/chronicle.

Understanding humans over long horizons requires agents to infer not only what people need in the moment, but also how routines form, why they repeat, and when they change. We introduce SimLife, a scalable platform for simulating long-term household life with rich visual observations, ground-truth action logs, and synthetic dialogues with audio. Built on SimLife, SimLife-BP evaluates long-context pattern understanding: the ability to infer latent behavioral rules from weeks or months of everyday observations. The benchmark contains 106 episodes averaging 15.49 hours and 38.57 in-game days, and 1,439 question-answer pairs. Each task probes direct, counterfactual, noisy, and inverse reasoning under different levels of rule hints. Evaluating frontier models and architectures, we find that current models often achieve surface-level prediction without comprehensive rule understanding, rely on frequency-based heuristics rather than if-then reasoning over evidence, and struggle to adapt when behavioral patterns change. These findings suggest that long-context pattern understanding remains a major bottleneck for future embodied agents, while SimLife opens a broader space for studying memory, personalization, adaptation, and long-horizon planning in everyday human-AI interaction.

Large language models (LLMs) have been applied to causal discovery, but candidate-graph generation rarely treats premature omission of potentially relevant causal relations as an explicit design objective. We propose MaSCoD, a multi-agent framework that organizes candidate third variables and local structural patterns before direct-edge judgment. We evaluate MaSCoD on Auto-MPG, DWD, and Sachs using GPT-5.4 as the primary backbone and GPT-4o for replication. MaSCoD exhibits a dataset- and backbone-dependent retention-selectivity profile rather than uniform superiority. Across all six dataset-backbone settings, Full, which supplies structural hypotheses before direct-edge judgment, achieved higher mean Recall and F1 than No Phase 1, which instead constructs them within the judgment procedure, while also increasing false-positive rates. Additional reference-edge retention over all evaluated baselines was observed on DWD with GPT-5.4 and on Sachs with GPT-4o, rather than uniformly across settings. Partial ablations showed that supplying both information components did not always outperform supplying only one. For GPT-5.4, stage-wise analysis showed that the Full-No Phase 1 retention gap was already present after direct-edge judgment, while reconciliation introduced additional reference-edge loss for Full on Sachs. These findings support structural pre-organization as an explicit design and evaluation target for omission control and motivate evaluating context construction jointly with its utilization in judgment.

Blind and low-vision users often need to locate a specific personal object rather than an arbitrary instance of the same category. The task calls for a robot that can move through the space and reach viewpoints the user cannot, and for an accessible interface where the user says which object is meant and learns whether the right one was found. We present RoboFind, a multi-agent framework in which a smartphone teaches the target and a quadruped robot carries out the search. A Target Teaching Agent converts guided smartphone recordings into a semantic target profile and a reusable multi-view reference bank through an accessible capture flow with AR guidance, speech and haptic feedback, and screen-reader support, so later missions refer to a stored object without repeating the teaching process. At runtime, a Navigation Agent explores the environment and proposes candidate targets, a Verification Agent checks each candidate against the stored references, and a Coordination and Recovery Agent completes the mission or triggers recovery and continued search. Across 32 real-robot missions, RoboFind reaches 85.0% success against 25.0% for a reconstructed sequential first-stop baseline over 20 trials with ten targets, and reduces false success from 75.0% to 5.0%. On six shared targets it succeeds in 10/12 trials, against 5/12 for 12 independently executed GPT-6 Astra-only trials. These results show that the multi-agent design fits the demands of personalized object search, where verifying object identity before declaring completion is what makes the outcome something a user can rely on.

LLM-based AI agents process user requests through iterative reasoning and tool execution, often involving the invocation of remote LLM APIs with local tool containers. This execution model can make the optimization of agent serving difficult because latency, local resource demand, and container bottlenecks inter-mix across requests. However, the current agent ecosystem runs without much consideration of resource dynamics, which results in significant waste of the precious resources. This paper analyzes the resource inter-mix of AI agents for three representative tasks: retrieval-augmented question answering, web search, and software coding. To this end, we characterize the latency with respect to the resource dynamics of processing multiple requests and tasks concurrently. Our measurements show that agents have a wide range of behaviors depending on tasks, so that even the same tool can differ substantially in resource dynamics. We also find that running multiple requests concurrently exposes task-dependent bottlenecks in resource dynamics such as CPU, disk I/O, and memory. Furthermore, we uncover that faster LLM responses or more CPU cores do not always accelerate agents. Based on these observations, we demonstrate new optimization opportunities that exploit the resource dynamics of tasks: CPU-aware tool admission and task-aware CPU allocation. Our results show that the latency of CPU-sensitive agent tasks improves $\sim$5.4$\times$, and the average latency across multiple tasks is reduced $\sim$32% compared to native agents.

Coordinating human analysts with autonomous AI agents faces the same challenges as human-to-human collaboration: sharing intermediate results, avoiding conflicts, and maintaining group awareness. Current tools rely on unstructured messaging or single-threaded chatbot interaction, which lack the structure to track evolving hypotheses or link claims to evidence. We propose agentic social data analysis, a collaboration paradigm extending social data analysis with a shared coordination feed modeled on the content timeline in social media services. We instantiate this concept in TREADSTONE, a platform where human and AI agents asynchronously post, link, and contest analytical claims via threaded messages within a shared feed. By allowing agents to proactively broadcast hypotheses and enabling users to steer the analysis through lightweight curation, Treadstone seeks to balance machine autonomy with human analytical control. A qualitative user study shows that Treadstone fosters collaboration while preserving human analytical agency, in contrast to the solitary experience of conventional chatbot interaction.

The rapid advancement of large language models and single-agent harnesses has reshaped the landscape of autonomous systems, raising a critical question of when multi-agent collaboration offers genuine value. As individual agent capabilities continue to scale, multi-agent collaboration faces diminishing returns while incurring growing context overhead. Through systematic analysis, we delineate the capability boundaries of multi-agent collaboration relative to single-agent alternatives, showing that it confers systematic benefits specifically in long-horizon tasks with sparse dependencies, while single-agent harnesses remain superior in tightly coupled, sequential workflows. Building on these insights, we propose SAIGE, a lightweight multi-agent collaboration mechanism based on Semantic-Aware Incremental Graph Evolution. SAIGE models collaboration as a dynamically evolving graph, where nodes are agent instances spawned on demand and edges encode semantic dependencies established through content-based information retrieval. Experiments on long-horizon, complex task benchmarks show that SAIGE achieves a favorable trade-off between context efficiency and task performance, and that scaling the agent pool or deepening the recursion level does not consistently improve outcomes. Our findings suggest that multi-agent superiority is bounded by task structure rather than universal, and that more agents do not necessarily make a system more intelligent.

Referring scene understanding for embodied robots requires grounding object- and relation-centric language queries from a designated viewpoint. While a local semantic Gaussian map can support such grounding within one agent's observations, cooperative settings require this ability to remain effective after independently reconstructed maps are aligned and fused. In this setting, the referred target or its contextual landmark may come from another agent's observations, while spatial relations must still be interpreted from the querying robot's viewpoint. We formulate this problem as cooperative referring Gaussian grounding over fused maps, which requires geometric alignability, instance-level semantic comparability, and view-conditioned relation reasoning. Existing language-aware Gaussian methods mainly focus on single-map querying, whereas Gaussian registration methods optimize geometric or photometric alignment without preserving language-grounding-oriented semantic compatibility. We propose CoRef-GS, a cooperative referring Gaussian splatting framework. CoRef-GS constructs local open-vocabulary instance-aware Gaussian maps, then aligns partially overlapping maps with a cross-agent alignment module by geometric and semantic consistency, and grounds queries using a view-conditioned mask relation graph. We further introduce CoQuad-Ref, a dual-quadruped benchmark spanning both real-world and simulated indoor scenes. Experiments show that, on simulated scenes, CoRef-GS reduces the rotation error from 2.58° after coarse initialization to 0.15° after refinement, and improves real-world referring mIoU over ReferSplat from 52.6% to 68.8%. The established benchmark and source code will be publicly released at https://github.com/ruojiruoli17/CoRef-GS.git.

Executable environments enable LLM agents to learn from the consequences of their actions. For embodied agents, those consequences extend beyond whether the current task succeeds: completing a delivery can consume the time, energy, or money needed for later work. Learning to plan therefore requires environments that preserve these dependencies and turn them into feedback across a complete trajectory. We introduce DeliveryGym, a 3D environment for evaluating and training agents on continuous courier shifts. It couples multimodal tool interaction with persistent world dynamics and computes trajectory rewards from simulator events, making the costs of an agent's decisions available for reinforcement learning (RL). The environment also adapts future training shifts to the policy's observed weaknesses while keeping evaluation fixed. Across six models and 13 city maps, evaluation exposes a gap between reliably executing assigned deliveries and choosing and sequencing work over a shift. On the unseen-city test set, RL improves Qwen3-VL-4B's net income by 54.3%, showing that learning from complete shifts improves performance under these coupled constraints. Adapting the training environment improves evaluation income by 18% over uniform sampling at 100 updates, indicating that which situations an agent practices also matters. DeliveryGym provides an executable setting for studying how agents learn to coordinate deliveries and preserve resources for later orders within an episode.

Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial inputs is largely unknown. We study the vulnerability of LLM trading stacks to black-box, input-only attacks that enter solely via admissible social-media feeds. We introduce the Generic Multi-Agent Trading System (GMATS), a framework that captures modern multiagent trading architectures and instantiate a class of black-box poisoning attackers that treat an LLM as a post generator and inject budget-constrained, plausibly benign social-media content into the analyst's evidence stream. We define contagion metrics that trace how adversarial content propagates through the stack, including belief-shift scores at analyst and coordinator layers and attack-clean deltas on standard backtest metrics. Experiments on a safe offline benchmark with historical market and social data show that even simple input-only attackers can materially degrade risk-return profiles, sharply reducing Sharpe ratios. At the same time, we find that suitably designed multi-agent topologies and coordinator prompts can dampen adversarial shocks and improve average robustness under identical poisoning budgets.

We present Astronex-World 1.0, an open controllable video world-model foundation. Given a text prompt (text-to-video) or an initial observation (image-to-video), the model predicts future visual states under frame-aligned camera trajectories, continuous actions, and an embodiment identifier, and accepts text events inserted at a specified position of a rollout. The family provides a bidirectional model for full-context generation and a causal model with block-causal attention and cross-block KV caching for persistent generation, both built on the Wan2.2-TI2V-5B prior. PRoPE injects camera intrinsics and extrinsics, while a 64-dimensional action stream modulates every Transformer layer. A five-stage training path develops bidirectional camera and action control, converts the backbone to block-causal generation, distills a few-step student, restores mixed-domain dynamics, and applies asymmetric DMD/DMD2 distribution matching. The causal model generates 832x480 video at 24 fps. All five training stages run on two NVIDIA L20 48 GB GPUs, and the causal model streams in real time on one. It scores 73.5 on WBench Navi and 70.0 on WBench Full. On Full, this 5B model is above the 13.6B LongCat-Video and the 14B Helios, within one point of the 22B LTX-2.3, and above YUME 1.5, which is post-trained from the same 5B prior on NVIDIA A100 GPUs. The reserved action input and output interfaces allow post-training for embodied intelligence and autonomous driving.

Geospatial foundation models can provide strong flood-segmentation performance, but their size limits deployment on memory-constrained edge hardware. We distill a 300-million-parameter Prithvi-EO-2.0 teacher, fine-tuned on the 252 manually labeled Sen1Floods11 training scenes, into a 0.7-million-parameter EfficientViT-B0 student. The teacher supervises additional unlabeled Sentinel-2 imagery, allowing the student training set to grow without new manual annotations. At the matched budget of 252 scenes, teacher-supervised training is competitive with direct training and improves STURM-Flood performance across tested configurations; a geometry-matched control shows that label source alone does not explain the difference. Scaling the teacher-supervised pool to 2,500 scenes narrows the remaining student--teacher gap: the float student reaches 0.787 water intersection over union on the Sen1Floods11 test split against 0.822 for the teacher, matches the teacher on STURM-Flood under our evaluation protocol, and remains below it on WorldFloods-v2. After activation replacement and quantization-aware training, the student runs as a 1.5-megabyte 8-bit integer (INT8) TensorRT engine on a Jetson Xavier NX at 5.57 milliseconds of graphics processing unit (GPU) compute per 512-by-512 image, with approximately 14 megabytes of runtime device memory. A fixed modified normalized difference water index (MNDWI) threshold is competitive with both models on the two clean external benchmarks, so we interpret those benchmarks as generalization tests rather than as evidence of learned-model superiority over a spectral rule. The results support the conclusion: foundation-model supervision can amplify a fixed manual annotation budget into a substantially larger training set and yield a compact, deployable edge model.