The Latest Papers about AI
-
Can Language Models Play the Wikipedia Game?
Abstract
Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist linguistic or scientific knowledge. We used the Wikipedia Game to test language models on an analogous information retrieval task. In the game, players must reach a target article using only article links. We compared sentence embedding models and LLMs across five Wikipedia languages and five academic-literature datasets. We construct very large local graphs of Wikipedia pages and of paper citations using OpenAlex and provide code to build and navigate them. This allows the study of language models' navigation capabilities without relying on third-party APIs. We compared the models with human and TF-IDF benchmarks. The Wikipedia Game format enables robust comparisons across techniques, languages, and domains. No model significantly outperformed humans, although the best models (GPT-o3 mini, GPT-4o, QwQ:32B, and DeepSeek-R1:70B) achieved comparable success. Performance and rankings varied across languages and topics, with implications for practitioners utilising these techniques.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13948
PDF
-
Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark
Abstract
In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function. Inspired by the literature on procedural and agentic generation, we present Artisan, a system that extends the latest method Articraft by introducing a multi-agent pipeline with physical simulation feedback, enabling comprehensive attributes beyond geometry, appearance, and physically plausible articulation, such as collision-free motion, stability under gravity, and accurate mass and material properties. Furthermore, we construct a unified benchmark spanning four key aspects: spatial fidelity, physical plausibility, downstream task performance, and overall quality. The benchmark encompasses 100 reference assets from ArtVIP and LightWheel, 50 stability prompts, and 50 ABO objects with reference masses, with protocols evaluating various metrics. Through extensive evaluation of more than 10 representative models, Artisan achieves competitive spatial fidelity while attaining the lowest collision rates and highest stability rates among the evaluated methods. Together, our system and benchmark establish insights for advancing 3D generation towards physically plausible, functionally usable assets.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13947
PDF
-
Splat2Act: From Captured Scenes to Personalized VLA Manipulation
Abstract
A user who brings a generalist manipulation policy into their home or office wants it to pick up their objects from their shelves, counters, and tables. Yet even a strong generalist like $\pi_{0.5}$ achieves 0% pickup success in our captured deployment scenes without adaptation, and collecting real demonstrations in every user's environment is prohibitively expensive. We present Splat2Act, an automated real-to-sim-to-real pipeline that personalizes a pretrained vision-language-action (VLA) policy to a specific scene and object set using only a handheld phone scan and images of the user's objects. Unlike prior real-to-sim work that reconstructs individual tabletops, Splat2Act operates on building-scale indoor environments: it builds a photorealistic digital twin with 3D Gaussian Splatting and collision geometry, automatically discovers tabletop and non-tabletop receptacles, constructs feasible pickup tasks, and generates successful demonstrations with a privileged simulation oracle, with only scene and object capture required from a human. Applied to 101 scanned campus environments with a median navigable area of 104.87 m$^2$ and 7 receptacles, the pipeline yields 852 receptacles and over 68,000 pickup demonstrations. We fine-tune $\pi_{0.5}$ in two stages: Stage 1 adapts to hundreds of public object assets, drawn either from the deployment scene alone or from all 101 scenes; Stage 2 personalizes to the user's own objects on the deployment scene's receptacles. Our strongest personalized policy reaches 62.5% aggregate pickup success in the target scene. Deployed on a real Stretch 3, the same policy achieves 63.9% success on a 12-task subset, closely tracking its 66.7% simulated success on those tasks. These results suggest that automated real-to-sim-to-real training can personalize VLA manipulation policies using only simulation-oracle data.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13945
PDF
-
InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators
Abstract
Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increasingly heterogeneous architectures and representations. Despite their remarkable generation capabilities, the cross-model alignment of latent representations and the consistency of their underlying denoising dynamics remain underexplored. In this work, we uncover an intriguing cross-model compatibility: independently trained generators exhibit similar latent spatial organization, while directly handing off intermediate states between unaligned models can still preserve coarse visual content. Motivated by these observations, we propose InstantFusion, a lightweight shared latent interface that connects the denoising trajectories of heterogeneous image generators. Specifically, to enable flexible cross-model state translation, model-specific Latent AutoEncoders (LAEs) are introduced to project intermediate states from different generators into a shared latent space and decode them into the latent space of a target generator. This shared space is constrained by two complementary objectives: aligning intermediate states derived from the same image at matched noise levels and synchronizing their corresponding local denoising velocities. Once trained, InstantFusion allows denoising to seamlessly transition across frozen generators without requiring a dedicated mapping for every model pair. The versatility of InstantFusion is demonstrated across acceleration, multi-preference composition, cross-architecture on-policy distillation, and cross-model composition, achieving competitive performance across these diverse settings.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13944
PDF
-
Noise Space Learning for VLA Adaptation
Abstract
Pretrained vision-language-action (VLA) models encode broad manipulation priors, yet adapting them to specific tasks requires balancing limited robot interaction, computational resources, and safety constraints. Noise space learning (NSL) adapts flow-matching-based VLAs by learning a context-conditioned distribution over noise while keeping the pretrained VLA fixed. Building on prior noise-steering methods, we formulate NSL as an interface for VLA adaptation that accommodates different learning algorithms and instantiate it with PPO, SAC, and AWR. Theoretically, we provide an information-theoretic analysis of how NSL enables efficient adaptation. Empirically, we study these NSL algorithms on LIBERO, RoboTwin, and four real-robot manipulation tasks under interaction, computation, and execution constraints. Across these settings, we develop a suite of effective NSL variants and derive practical recommendations for choosing among them under different resource and deployment regimes.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13943
PDF
-
Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback
Abstract
Multimodal diffusion transformers (MMDiTs) allow the evolving image to update internal text representations through joint attention. These representations then guide subsequent image updates, raising a question: does this feedback help correct deviations from the prompt, or preserve them? We find that image-to-text (I2T) feedback can preserve the objects and attributes already represented in the evolving image, including errors. Transplanting I2T messages can rescue failures or disrupt successes. At matched intervention strengths, suppressing the influence of I2T feedback improves generation, whereas opposite controls degrade it. These findings motivate Semantic Feedback Guidance (SFG), which suppresses the influence of I2T feedback by guiding away from an auxiliary branch that strengthens this feedback and weakens text-to-image conditioning. The in-place variant, iSFG, directly suppresses I2T feedback and strengthens text-to-image conditioning, requiring no extra model evaluations. Temporal interventions motivate running the SFG branch during the first 20% of image sampling steps, requiring about $1.2\times$ the base NFE without classifier-free guidance (CFG). Experiments across three image-generation backbones show gains in alignment and preference-model scores. On FLUX, adding SFG to CFG raises GenEval from $0.6661$ to $0.7479$; on SD3.5M, iSFG adds $+1.33$ HPSv2.1 over CFG at zero extra NFE. The control also transfers to text-to-video and image-to-video generation, improving VBench scores. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13941
PDF
-
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
2026-10-09 17:56:59Abstract
Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can only interpret classification and regression models. They require access to model weights or large concept-annotated datasets, and most methods cannot provide image-level attribution. We propose Hide and Seek (HnS), a new method for concept-level attribution that does not require access to model weights or labeled concept datasets. HnS can interpret a wide range of vision models. Given a concept and image set, HnS retrieves concept-aligned images using a vision-language model, localizes the concept within each image, masks the localized region, and measures attribution from the change in the black-box model's output between the original and masked images. This enables faithful attribution by directly measuring the model's behavior and supporting local attributions. We validated HnS on CelebA and COCO-Stuff. Compared to existing methods, HnS showed better agreement with ground-truth attributions. We demonstrated the applicability of HnS on diverse tasks, including image captioning and satellite image segmentation, where no existing concept attribution method can be used. We provided our anonymous code in the supplementary material.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13935
PDF
-
Chronos Policy: Learning Robot Policies on Physical Time
2026-10-09 17:55:20Abstract
Robot policies often convert sensing and control into fixed-rate observation-action sequences, leaving physical time implicit in sequence position. This assumption breaks when observation rates or delays vary, or when inference latency changes. We introduce Chronos Policy, which makes physical time explicit by conditioning on observation capture times and desired action execution times. We study two ways to incorporate time into a diffusion transformer: adding timestamp embeddings to token features, or encoding physical time in positional encoding through time-aware rotary positional encodings (time-aware RoPE). We find that time-aware RoPE is more robust, allowing attention to depend directly on physical time while keeping token content unchanged. During training, we temporally randomize which observations are sampled and when the action chunk begins, exposing the policy to a wider range of sensing and execution schedules that may occur during deployments. This also enables learning from asynchronous, multi-rate data without forcing all measurements onto a fixed temporal grid. Across simulation and real-world experiments, Chronos Policy improves performance on dynamic tasks, where observation-to-action timing is critical, and on multisensory tasks, where the relative timing between observations matters. On standard quasi-static tasks, it preserves nominal performance while improving robustness to changes in sensing and inference timing.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13929
PDF
-
Can machines reason non-verbally?
Abstract
Modern machines can solve equations, follow logic and reason through language, yet they still struggle with problems that require visual non-verbal reasoning. This is evident even in advanced systems such as DeepSeek, ChatGPT and Gemini, which remain limited on visual tasks such as completing abstract patterns or delineating ambiguous regions-of-interest. Unlike explicit intermediate steps in verbal reasoning which can be verified through logic or automated tests, visual reasoning involves implicit intermediate steps with no clear methods for verification. Non-verbal reasoning is therefore challenging to model and, as a result, remains a fundamental limitation of current machine intelligence. Here we introduce GenVerOpt, a general framework that unifies generation, verification and optimisation into a reasoning pipeline for machines. By generating candidate solutions, verifying their correctness, and iteratively refining them, GenVerOpt enables per-sample optimisation rather than relying solely on dataset-level trends captured during model training. This process mirrors human problem-solving where multiple possibilities are imagined, evaluated, and refined until a correct solution emerges. Across diverse domains, GenVerOpt demonstrates capabilities beyond existing systems: it surpasses humans on abstract IQ puzzles, matches clinicians in prostate cancer segmentation, exceeds experts in liver vessel reconstruction and outperforms state-of-the-art approaches in tumour boundary alignment. These results show that machine reasoning can extend beyond language, establishing visual non-verbal reasoning as a foundation for more flexible and generalisable intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13925
PDF
-
Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning
Abstract
Self-supervised learning on 3D medical images commonly relies on random sub-volume sampling during pretraining. However, random cropping implicitly treats all spatial regions as equally worth observing, despite anatomical priors and spatial redundancy that make regions inherently unequal in their value for representation learning. To this end, we first show through controlled crop-quality manipulations that better sub-volumes lead to better downstream transfer, revealing the observation policy as an overlooked bottleneck in 3D medical SSL. Motivated by this finding, we revisit sub-volume sampling as a \emph{where-to-look} problem. We propose \textbf{\method}, a plug-and-play framework that replaces random cropping with an offline coarse-to-fine probe bank guided by \textit{anatomy-awareness}, \textit{informativeness}, and \textit{diversity}. We instantiate \method as a lightweight \lite variant using geometric and image-statistical cues, and a diagnostic \feat variant using frozen visual features, to examine whether lightweight volume-intrinsic priors suffice or richer semantic cues reliably provide additional value. Extensive experiments across multiple 3D medical SSL backbones and downstream tasks demonstrate that \method-\lite consistently improves transfer performance over random sampling. Mechanistic analyses further attribute these gains to more anatomically plausible and informative observations, reduced spatial redundancy, more efficient learning dynamics, and more structured representations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13915
PDF
-
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
Abstract
Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything, a domain-general framework built on JEPA-Anything that uses predictive world models to guide action and learning-data selection. Observed feedback drives policy or workflow improvement and conditional world-model adaptation, while component and compatibility checks govern the retention of updated policy-model pairs. Across diverse computational and scientific domains, RSI-Anything demonstrates substantial gains. In code repair, with the coder fixed, success increases from 26.3% with a static verifier to 29.2% through predictive selection and 31.2% after world-model adaptation, at comparable test usage. Graphical user interface (GUI) evaluations showed higher task completion, while average actions decrease by 39.4%. Across five successive policy versions, laboratory-planning scores more than double from 21.80% to 46.01%. In reaction optimization, RSI-Anything achieves 96.15% mean best observed yield versus 82.16% for Bayesian optimization under the same 40-experiment budget. An end-to-end immune-science application further connects workflow evolution and predictive modeling with therapeutic hypothesis generation. These results demonstrate how predictive world models and retained system updates enable recursive improvement across diverse environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13912
PDF
-
When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors
Abstract
Vision-Language Models (VLMs) increasingly analyze and reason about images, yet it remains unclear whether their internal representations faithfully encode the structured relations required for such reasoning. We introduce EICS (Evaluation-Invariant Concept Stability), a metric for testing whether representations consistently encode concepts under controlled one-concept interventions, and CASP-VL (Causally controlled Spatial Perturbations for Vision-Language models), a benchmark of causally controlled spatial perturbations derived from Visual Genome scene graphs. Across multiple VLM architectures, we find that spatial relations are represented substantially less faithfully than lexical information, even when the same models score well above chance on compositional benchmarks. Further analysis shows that the relation is identifiable at the predicate's own tokens but is lost when the sentence is aggregated into a global representation, whether through the (EOS) token or by mean pooling. These findings reveal a systematic failure invisible to output-based evaluation: VLMs do not preserve, in the representation used downstream, relational information that is present in their own input.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13910
PDF
-
Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping
Abstract
While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Several lines of research offer alternatives to the standard Mean Squared Error (MSE), but differences in datasets, backbones, and evaluation protocols make their practical benefits difficult to compare. In this work, we address this gap by performing a systematic re-evaluation of regression objectives across a broad collection of established tabular datasets and multiple neural backbones. Our comparison reveals that many proposed objectives provide limited or inconsistent gains over a properly tuned MSE baseline, while quantile loss yields consistent aggregate improvements over MSE across the tested backbones. We then identify a limitation that remains even with this strong objective: regions with different levels of target noise can reach their best predictive performance at different training epochs. Consequently, a single global early-stopping checkpoint can impose a compromise between uncertainty regions, even when the objective can represent heteroskedastic target distributions. Motivated by this limitation, we introduce a heteroskedasticity-aware extension of quantile loss that uses input-dependent label smoothing as a potential remedy and improves over quantile loss on several backbones. Overall, our results provide a modern empirical picture of regression objectives for tabular deep learning and highlight how differences in optimal stopping times across uncertainty regions can limit the effectiveness of global early stopping. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13909
PDF
-
Structural Automata for Neural Semantic Parsing
Abstract
Neural semantic parsers generate meaning representations token by token, yet well-formedness depends on references, scope, and graph relations that unfold during generation. Constrained decoding prevents locally invalid tokens but does not guarantee that a valid prefix can be completed within a fixed output-length limit. We investigate structural automata at three stages of DRS parsing (decoding, post hoc processing, and training) and additionally evaluate decoding on AMR. For decoding, we introduce accepting-path decoding (APD), which maintains a verified completion within the remaining length limit and follows the model's preferred token whenever that token can also be completed. APD guarantees an accepted output without retracting tokens. Under tight length limits, it improves Smatch++ over local masking by 5.1 and 2.4 points on DRS and by 6.4 and 3.2 points on AMR, comparable to rollback under the same limit, which retracts tokens. For post hoc processing, invalid outputs concentrate on the same inputs: eight unconstrained samples yield no valid output for 10.2% of inputs with limited training data, compared with 0.4% with full data, where filtering comes within 0.2 Smatch++ points of APD. For training, penalizing automaton-rejected tokens improves development Smatch++ by 3.6-11.0 points after 10% of training, but this advantage diminishes as cross-entropy alone reduces the probability assigned to rejected tokens from 14% to below 2% within the first sixth of training with limited data.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13896
PDF
-
Task Context Shapes Component Roles in Language Models
Abstract
Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in each task. A natural source of inspiration is task-dependent interactions among shared brain regions, which motivate a network view of language-model computation. Here, we compare fixed model components across tasks using identical graph facts, statements specifying which directed connections are present. We measure how interventions affect attention heads and the activation state in later layers (influence), as well as the answer (importance). Task changes redistribute the influence in five open-weight models spanning four families and 1.5-14 billion parameters. In Gemma-2-9B and Qwen3-14B, an activation edit changes an early internal activation vector and switches which fact the model reads while the written instruction stays fixed. The same heads then respond to different graph facts and influence later components differently. For each prompt, we construct two linear response maps, one before the edit and one after it. Each map predicts a later head's response from a measured change in an earlier head. For a separate factual intervention, the map for the corresponding condition reduces mean squared prediction error by 53.6% in Gemma and 5.0% in Qwen compared with the average of the two maps. These findings show that task context changes both which graph facts the shared components respond to and how their outputs affect later computation. A network account may help explain how models use shared parameters to perform different computations. Measurements of task-dependent influence could also guide interventions intended to alter one behavior while preserving others.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13895
PDF
-
Beyond the Snowflakes: Disentangling Weather Effects from Confounding Meta-Factors in LiDAR Object Detection
Abstract
Light Detection and Ranging (LiDAR) is critical for autonomous perception, yet its performance is known to degrade in adverse weather. While existing literature models snow as atmospheric noise that degrades performance, our granular evaluation on the WADS-3D and CADC datasets reveals a counter-intuitive phenomenon: detection accuracy consistently improves as snow intensity increases. Through ablation study and meta-information analysis, we reconcile this by confirming that while falling snow acts as noise, its negative impact is outweighed by a dominant, concurrent factor: significantly increased object point count. We hypothesize that this object point count boost acts as a geometric enhancement, driven by snow accumulation increasing vehicle surface area and a shift from specular to diffuse reflectance. Our findings demonstrate that evaluating perception systems using broad weather-severity bins without accounting for correlated object-level data can lead to misleading conclusions about detector robustness. We conclude that accurate evaluation requires decoupling atmospheric noise from surface accumulation effects and outline future research to validate these physical models. The WADS-3D dataset is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13891
PDF
-
RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics
Abstract
As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availability during execution. To address this gap, we propose RATED (Reliability-Aware Tool Retrieval via Execution Dynamics), a retrieval framework that combines robust semantic matching with dynamic reliability adaptation. RATED employs a frozen dual-encoder with contrastive fine-tuning for semantic matching, and a lightweight contextual bandit module that re-ranks candidates based on real-time execution feedback. This design enables rapid adaptation to runtime tool failures without expensive model retraining. We introduce EcoAgent, a benchmark of 5,172 real-world tools and over 210,000 query-tool pairs for offline retrieval and dynamic reliability evaluation. Experimental results demonstrate that RATED achieves a 52.2% relative MRR improvement over the ToolLLM API retriever on real-world queries, and reduces fault selection rate from 86.2% to 2.9% under severe API outage scenarios with a 30% failure rate, while incurring negligible latency overhead of less than 1 ms over encode-only inference. The code and dataset are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13889
PDF
-
X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems
Abstract
Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, unintended or harmful outcomes can arise when agents fulfill benign user requests. Proactively identifying these compositional failures requires systematically exploring diverse cross-service paths. Existing red-teaming methods often simply prompt LLMs to identify potentially harmful paths from task and environment descriptions or decompose harmful objectives specified by humans or LLMs into seemingly benign action combinations. However, generation is biased toward patterns learned during training, potentially favoring familiar tool combinations and leaving novel cross-service interactions underexplored. To address this, we propose X-AgentRed, a self-evolving red-teaming framework that discovers harmful tool call paths through a graph of tool dependencies and expands and refines them using execution feedback. By analyzing each tool's effects, potential harms, and preconditions for execution, the red-teaming agent constructs a directed graph that captures how one tool's effects can satisfy another's execution preconditions. Recipes sampled from this graph are instantiated as realistic scenarios in which agents can produce harmful outcomes. Execution feedback enables self-improvement by diversifying paths that produce harm through tool substitution and refining preconditions at blocked steps in unsuccessful paths to enable further execution. Across four frontier agentic models, X-AgentRed achieves $1.77\times$ the harmful path rate of STAC and explores a more diverse set of tools, yielding $2.99\times$ the tool coverage on average.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13886
PDF
-
Tracking the Invisible: Self-Supervised Wheel Track Detection with Thermal-RGB Fusion
2026-10-09 17:21:28Abstract
Accurate detection of drivable area is essential for autonomous driving and advanced driver assistance systems. While state-of-the-art methods focus on general traversability estimation, they prove inadequate for snow-covered roads where following existing wheel tracks offers crucial advantages: improved traction, predictable vehicle dynamics, and verified path stability. To address this, we propose a low-cost, self-supervised approach detecting safety-critical wheel tracks using synchronized RGB-I (RGB + Long-Wave Infrared) imagery. Our method automatically generates training labels by projecting future wheel trajectories from recorded GNSS data. A neural network is designed to identify wheel tracks with the 4-channel RGB-I images from challenging, white-out road surfaces. Experimental results demonstrate the effectiveness of our approach in visually monotonous and featureless adverse environment, offering a robust and cost-effective alternative for winter autonomy. The newly introduced ThermalTrack dataset is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13872
PDF
-
BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation
Abstract
Deploying language-model agents onboard mobile robots requires task reasoning and responsive execution within limited compute and memory. We propose BT-Agent, an onboard architecture combining LLM-driven task decisions with predefined behavior-tree (BT) skills. These skills enforce execution conditions and return structured failure feedback. We demonstrate fully onboard operation with a 9B model on a quadruped across five task categories. Intervention tests show that local checks stop ongoing navigation without waiting for another model decision, while the agent remains active to retry or report constraints. To compare agent designs efficiently, we introduce a 161-task multi-fidelity benchmark, evaluated in text on all tasks and in Habitat on 39. Text supports 10.9$\times$ higher evaluation throughput, while simulation reveals how perception and motion failures change task outcomes. BT-Agent's largest success gains over the strongest Act/ReAct baseline occur at 4B and 9B: approximately 10 and 5 percentage points. Ablations identify structured tool calls and informative failure feedback as the most useful components.
Abstract (translated)
URL
https://arxiv.org/abs/2610.13862
PDF
