每天知道
你的领域
出了什么

Adapting robots to new objects and tasks requires interaction experience that can be costly to obtain. We present WorldContact, a contact-centric world model for deformable-object manipulation, constructed from a limited set of high-quality trajectories to generate additional training data efficiently. It predicts object dynamics using larger time steps than the source numerical simulator, which requires small integration steps to resolve rapid motion and prevent interpenetration. We evaluate WorldContact across 16 shopping-bag manipulation tasks. State-rollout measurements on a single H100 GPU show a $10\times$ speedup over the source simulator, excluding rendering and disk I/O. We use the generated data to fine-tune an existing vision-language-action policy and deploy it directly on a real robot. In bag lifting, the same policy achieves 65% single-attempt success when fine-tuned on source simulation data alone, compared with 95% when fine-tuned on the dataset expanded with WorldContact. These results support efficient data generation with WorldContact for robot policy adaptation.

Human manipulation videos provide rich motion and interaction cues for acquiring robot skills without robot demonstrations. Video generation models synthesize such demonstrations from an initial scene image and task instruction, avoiding the need to record demonstrations for each task. However, the recovered motion captures only one scene-specific realization, leaving task structure, geometric relations, and constraints implicit. We present V2-STRep, a zero-shot framework that converts generated video motion into reusable robot skills through VLM-grounded structured task representations. The representation specifies motion phases, references, and task-relevant constraints, with targets described by minimal geometric structures: points, point-normals, axes, planes, and full 6D poses. VLM-provided 2D image-space cues are lifted into 3D using RGB-D observations to reconstruct task geometry and candidate grasp poses. Geometry-specific rules transfer motion to new scenes, while task-constrained trajectory optimization couples grasp selection with complete robot motion planning. It preserves task requirements while using remaining rotational freedom to accommodate joint limits. Updating deployment grounding and constraints enables reuse under new compatible instructions without generating another video. Experiments on six real-world manipulation tasks demonstrate improved execution success over baselines, reliable cross-scene transfer of successfully acquired skills, and adaptation to changed deployment instructions.

Learning predictive models of contact-rich dexterous manipulation requires dense tactile interaction, but such data are costly to scale on real robots and remain tied to embodiment-specific sensors. We introduce DexTouch-WM, an action-conditioned world model that learns from scalable human touch to jointly predict future RGB observations and bilateral tactile dynamics. Our insight is that human and robot manipulation share transferable contact dynamics when their tactile observations and action spaces are made compatible. We deploy flexible piezoresistive arrays with a shared sensing layout on both human and dexterous robot hands, and retarget human motion into the robot action space so that human interaction can supervise the same dynamics model used for real-robot prediction. DexTouch-WM couples a pretrained video expert with a lightweight tactile expert using anatomy-aware tactile tokens and aligned action conditioning. In human-to-robot scaling experiments, we keep five hours of real-robot supervision fixed while increasing human interaction from 0 to 100 hours, and observe substantial improvements in held-out robot-domain visual, geometric, and contact prediction despite disjoint human and robot task sets. Beyond prediction, we evaluate the world models as surrogate environments for policy evaluation and as generators of synthetic trajectories for real-robot policy learning, showing that scalable human interaction provides a complementary data axis for learning dexterous robot world models.

Between a screenplay and a film sits a planning problem that is spatial first: who stands where, and what a camera sees from where it stands. An image diffusion model asked for a shot in free text settles that plan by its own defaults. We present PACE (Precise AI Cinematic Expression), a typed representation for the plan: the screenplay evidence, the characters, props and locations it needs, where each subject stands, and what the camera does. A value is written once at the level it belongs to (script, scene, shot or panel) and inherited below it. A compiler turns the result into both the prompt sent to the diffusion model and a 3D scene built in metres, and a camera solver places the camera so that the declared framing is the framing built. Where a declared value becomes geometry, PACE measures, field by field, how far the compiled camera and the staged render sit from the declaration, rather than asking a model to judge. On the 11-scene Automatic Drive screenplay, every staged single-subject panel places its subject within 1.2% of frame width of its declared position; with two or three subjects one camera pose cannot satisfy every position, and the residual is reported rather than absorbed. On 204 external director-storyboard shots, delivered head height is 1.906 times the staged target from the director's words, 1.733 from the compiled prompt, and 0.955 with the greybox control; the condition that holds framing best draws the described action least. Declaring the pose on 30 shots raises the action drawn from 58.9% to 74.4% without moving the framing. Transitions, fitted motion and human review of the generated panels remain open. Code: https://github.com/StudioPiLabs/pace-core

Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and colorization, but often relies on dedicated color representations or specialized inference procedures. Advances in large language models offer a simpler starting point: even compact models can associate hex values with color semantics. We present Paint-Anything, which learns a shared hex-prompt interface for generation and editing through object-level color supervision. We develop a data pipeline that constructs Paint-500K from real images through object grounding, perceptual color labeling, and editing-pair synthesis. Since shadows make real-image labels only approximate colors, we complement this supervision with pure-color anchors whose pixels exactly match their paired hex values. These anchors are used only at high-noise timesteps, leaving low-noise training to natural images. We further introduce Any Color Benchmark (ACBench), comprising ACBench-T2I and ACBench-Edit, to measure object-level hex color fidelity across both tasks. On FLUX.2-4B, Paint-Anything improves ACBench-T2I and ACBench-Edit scores by 85.3% and 28.3%, respectively, relative to the base model, with ablations supporting the training recipe. It also achieves the highest average CompColor score among the compared methods.

Text-guided image editing must introduce the requested changes while preserving unrelated source content. In training-free editing, diffusion editors often use spatial controls whose inaccuracies can leave edits incomplete or alter unrelated regions. Causal autoregressive editors face a further constraint: their fixed decoding order limits revision of earlier decisions. As the first to explore training-free image editing with Generative Refinement Networks (GRN), we observe that its refinement process is inherently suitable for editing and offers a promising way to address these limitations. Motivated by this observation, we introduce RefineEdit, a training-free prompt-to-prompt image editing framework built on the GRN. Our key idea is to couple edit localization with content generation through the global refinement of binary image codes, allowing editing evidence to be revised as the image evolves. More specifically, RefineEdit combines bit routing with two stabilization mechanisms: adaptive spatial freezing and finite bit locking. Bit routing starts from an intermediate source state and uses signed probability differences between the two branches to identify editable positions and bits. It directs selected bits toward editing refinement while anchoring the rest to the evolving source trajectory. Adaptive spatial freezing limits unnecessary expansion of the editing region, while finite bit locking maintains recent bit activations to support continued editing. The overall framework requires no additional training, external masks, or attention control. Across nine editing categories of PIE-Bench, RefineEdit achieves the best background-preservation scores in PSNR, LPIPS, MSE, and SSIM, together with the highest whole-image and edited-region CLIP scores among the evaluated methods. Code is available at https://github.com/mura1n/RefineEdit.

The existing singularity-free guiding vector field (SF-GVF) with an additional virtual coordinate can eliminate singular points (i.e., points where the vector field vanishes) inherent in conventional GVFs and guarantee global convergence of robot trajectories to closed and self-intersecting desired paths. However, the desired speed given by the GVF along the desired path in the original lower-dimensional space cannot be arbitrarily specified but depends on path parameterizations. One possible workaround is to partially normalize the physical projection of the SF-GVF and assign a user-designed speed. However, we show that this workaround may introduce new singularities since the normalization denominator can become zero. To address this issue, we propose a new SF-GVF with prescribed physical speed (PPS). The integral curves of the new SF-GVF converge exponentially to the desired path from any initial condition in the higher-dimensional space (including virtual dimension); more importantly, the robot's physical speed converges to the PPS, while the path-error dynamics remain invariant under regular reparameterizations of the desired path. We further develop a saturated acceleration control law for second-order kinematic models. Finally, comparative simulations and 3D path-following experiments with a quadrotor under different PPS profiles validate the theoretical results and demonstrate the effectiveness of the proposed approach.

Heterogeneous federated learning requires clients with diverse computational capacities to collaboratively train a global model, where each client trains a capacity-constrained submodel. Existing methods select submodel parameters using heuristic importance measures---most prominently parameter magnitude---without theoretical justification for why these measures support convergence. We identify a fundamental gap: existing parameter selection criteria lack theoretical grounding in the convergence framework, partial client participation introduces additional estimation effects in the Fisher scores. We propose FedFIbOS: Fisher Importance-based Optimal Submodelling for heterogeneous federated learning, using Fisher Information in a principled criterion derived from minimizing submodel masking error. %We formally establish when magnitude selection is equivalent to Fisher selection fail under non-IID heterogeneous federated learning. We theoretically formulate submodel selection through a Fisher-weighted quadratic masking surrogate and show that the raw Fisher top-$k$ rule implemented by FedFIbOS solves this surrogate under a Fisher-dominant ranking condition. The resulting method retains the convergence structure of the underlying masked federated optimization bound. Fisher scores are efficiently estimated from empirical diagonal Fisher information using squared gradients, enabling stable and adaptive parameter selection without additional optimization overhead. Experiments on CIFAR-10, CIFAR-100, and AGNews under pathological and Dirichlet non-IID settings show FedFIbOS achieves ${\approx}10%$ higher accuracy than the state of the art, with improvements becoming more pronounced under stronger heterogeneity.

Gromov--Wasserstein optimal transport (GW-OT) extends classical optimal transport by introducing structure-aware transport cost. This is particularly relevant for spatial transcriptomics, where dynamical reconstruction should preserve tissue structure in addition to matching expression patterns. While static formulations have been widely used for such structure-aware alignment, a general dynamic formulation for reconstructing continuous trajectories is still missing. We introduce Travelling Pair Dynamical Alignment and Trajectory Estimation (TP-DATE), a theoretical and computational framework to generalize GW-OT dynamically in a simulation-free manner. We formulate a broad class of static and dynamic Quadratic-form OT (QOT) through path actions and prove the static dynamic equivalence. We further develop travelling-pair flow matching, which allows interacting conditional paths and marginalizes their interactions into a single vector field. On synthetic and real spatial transcriptomics data, TP-DATE better preserves spatial structure and improves continuous 3D dynamics reconstruction.

Few-step distillation reduces the inference cost of image-to-video generation, but directly reusing LoRA adapters trained for long denoising trajectories can weaken their intended effects and degrade video quality. We observe that adapters with similar measured static parameter geometry can behave differently under the shortened target schedule, motivating response-aware transfer. We propose DART, a training-free reparameterization method that transports source LoRAs into aligned coordinates through a low-rank distillation bridge. Paired forward evaluations measure channel-level incremental responses under the target schedule to fit coefficients that calibrate response direction, source-relative magnitude, and timestep allocation. Coordinate transport establishes update directions, while calibration adapts their contributions, requiring neither source training videos nor backpropagation. Experiments across multiple distilled I2V models demonstrate improved generation quality and aggregate functional retention over direct reuse. Further analyses show that coordinate transport complements response calibration, with adapter-level benefits encompassing both functional preservation and reduced negative transfer.

Characterizing the physical properties of clay and cementitious materials matters across many fields, from materials science to geological waste disposal. Property simulation typically calls for 3D imaging, which is expensive, not always accessible, and technically limited for certain materials. Recent progress in deep generative models offers a way around this, reconstructing 3D volumes from the more easily acquired 2D images. Among GAN-based methods for 3D microstructure generation, SliceGAN has shown strong results for homogeneous isotropic and anisotropic systems. It struggles, however, to capture the finer detail of more complex heterogeneous microstructures, which motivates alternative generative frameworks. We introduce a hybrid approach that draws on the stability and generation quality of denoising diffusion models. Since no 3D ground truth is available, we replace the standard denoising loss with an adversarial loss, which yields a stable training process in our experiments. We show that the resulting model generates microstructures of varying complexity with minimal slice artefacts and close agreement with ground-truth phase fractions and structural descriptors.

Flow matching has emerged as the state-of-the-art generative model and has been used for plug-and-play (PnP) priors to solve inverse problems in computational imaging. However, existing flow-based inverse solvers assume linear forward models and/or make simplifying approximations in posterior sampling. To circumvent these problems, we introduce FlowSGS, a flow-based posterior sampling method using Split Gibbs Sampling (SGS) to decompose the posterior into a likelihood step and a prior step. Specifically, we sample from the likelihood step using Langevin dynamics and leverage the Stochastic Interpolants (SI) framework to integrate a pretrained flow model into the prior step. We provide a form for the prior step that uses SI's reverse-time SDE, and show connections to previous PnP methods. Moreover, with the aid of the flow prior's straight probability paths and a novel timestep correction technique for the reverse-time SDE, FlowSGS requires fewer network evaluations in its prior step than plug-and-play diffusion samplers. Our experiments show state-of-the-art performance on a range of inverse problems. For the first time, we provide an experiment on a nonlinear inverse problem (Fourier phase retrieval) for flow-based inverse solvers.

To keep coding agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before it runs (Auto Mode in Claude Code, Guardian in OpenAI's Codex). Prior evaluations of such monitors largely measure robustness to accidental harm or prompt injections from untrusted sources looking to hijack the agent. Less understood is how they hold up when the agent they monitor is persistently misaligned. To understand this risk, we task an adversarial agent with evading production blocking monitors and causing catastrophic harm, e.g. by exfiltrating its own weights. We find that when instructed with high-level attack strategies, adversarial agents can succeed through several distinct mechanisms, such as agent-generated prompt injection against the monitor, multi-agent attacks, and malicious compaction. In particular we find that in 79% of trials, the agent can use an injection attack against Auto Mode and Guardian to run arbitrary bash commands. We also find that it is possible to greatly improve Auto Mode through design changes like enhancements to tool coverage, changes in transcript formatting, and the addition of an agentic monitor stage. Even with these improvements, preventing multi-context attacks at an acceptable cost remains an open problem. By detailing our red-teaming methodology and highlighting new attack vectors, we aim to help defenders evaluate their mitigations against the possibility of persistent malign coding agents. Code is available at https://github.com/safety-research/red-teaming-auto-mode.

Predicting the future trajectories of surrounding vehicles in autonomous driving is important for collision risk assessment and safe ego-vehicle path planning. Conventional neural network-based trajectory predictors typically achieve strong prediction performance by exploiting agent history, dynamic scene graphs, and semantic maps. However, in specific motion regimes such as acceleration, deceleration, and turning, these predictors may fail to reflect physically feasible trajectories. To address this issue, this study proposes a framework that fuses the output of Trajectron++, a neural network-based trajectory predictor, with extended Kalman filter (EKF)-based multiple trajectory candidates at a late stage. On the nuScenes dataset, the proposed method reduces the average displacement error and final displacement error of the Trajectron++ robot baseline by 13.7% and 14.6%, respectively, without modifying the baseline architecture. These results indicate that EKF-based trajectory candidates can effectively complement neural trajectory prediction through learned fusion.

Retrieval assembles repository context by ranking passages for relevance to the current query. A coding agent halfway through an issue has already read much of what such a ranker returns. Relevance is scored per passage, but sufficiency belongs to the set: independently scored passages can fill the budget with support for one requirement while another goes unmet. We formulate state-conditioned minimal sufficient evidence recovery: given a captured agent state, recover a compact evidence combination supplying what its next decision still lacks. SERBench measures this on 500 held-out states from 45 repositories, recording what the agent has seen, crediting only sets that satisfy every annotated evidence requirement of the current decision, and separating set recovery from candidate discovery. MSS-Complement treats acquisition as set construction, not ranking. Three semantic calls propose a jointly sufficient set, search for what it lacks, and return 4-8 intact source units within 6,144 tokens. One configuration, fixed on calibration data, recovers a complete set for 73.0% of those states at five items and 80.6% at eight, against 61.4% and 72.4% for Qwen3 embedding with reranking. A matched control ranking by similarity alone recovers fewer complete sets, placing the margin over it in the set-level policy, not the computation. The lead persists from frozen repository source with no gold-derived pool. On AMA-Bench it answers from a 76.2% smaller answer prompt, with accuracy 2.08 points above that benchmark's own memory agent. Removing one required group from a complete set costs repair-localization precision under two executors. Retrieval for agents is better posed as recovering what a decision lacks than re-ranking what an issue resembles.

We study GPT-6-Astra in a zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) system, where it interprets instructions, assesses its surroundings, and proposes actions. The system uses a common observation--decision--execution workflow with direct model API calls, without a packaged agent harness or navigation-specific fine-tuning. In this workflow, each request receives selected observations, execution feedback, and retained progress records. Evaluation covers the complete system, including context management and action control. We evaluate the system on 50 of the 100 R2R-CE val-unseen episodes used by Open-Nav. It achieves a success rate of 52.0%, an SPL of 48.9%, and an nDTW of 70.8%. Our analysis highlights three findings. First, recorded responses link landmarks and earlier actions to instructions using observations and supplied history. Second, reviews include requests for additional views and revisions of uncertain judgments. Third, the results suggest a gap between task understanding and autonomous completion: an unfinished crossing is recognized while rotation continues. At termination, 36.0% of episodes succeed with a workflow-accepted STOP, while another 16.0% meet the distance criterion at the step limit. These results highlight a central challenge: translating correct local judgments into sustained progress and appropriate stopping.

Large language models are usually interpreted through concepts that humans already possess: truthfulness, refusal, deception, personality, harmfulness, and related categories. This paper asks whether models may also represent and use distinctions for which no adequate human concept exists. We call such internal structures xeno-representations, and their study xeno-interpretability. We distinguish the human-interpretable semantic space from the xeno-semantic space: the region of model-native representations for which no adequate human conceptual counterpart is available. We show that the space of possible internal distinctions in an LLM is substantially larger than the space available through finite human descriptions. We then separate experimental identification from semantic interpretation: an internal representation may be reproducibly located, geometrically characterized, causally manipulated, and linked to downstream behaviour even when its semantic content cannot be adequately expressed in human terms. On this basis, we sketch an empirical programme to identify xeno-representations. We finally examine the implications for AI safety and multi-agent systems, where model-native representations may propagate and stabilize across interacting agents while remaining only partially visible through human-readable communication. Xeno-interpretability therefore shifts the aim of interpretability from finding human concepts inside models toward discovering and characterizing the representational structures that are native to the models themselves and might affect their behaviour in unpredictable ways.

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.