arXiv subjects

Hao Wu

Publications and source records attributed to Hao Wu.

7 recordsLinked to original sources

arXiv2026

UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents

Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However, existing research exhibits inconsistent interaction representations, largely overlooks the structural distribution of tool-use trajectories, and relies on incompatible evaluation benchmarks. We present UniToolCall, a unified framework for tool learning that standardizes the entire pipeline from toolset construction and dataset generation to evaluation. The framework curates a large tool pool of 22k+ tools and constructs a hybrid training corpus of 390k+ instances by combining 10 standardized public datasets with structurally controlled synthetic trajectories. It explicitly models diverse interaction patterns, including single-hop vs. multi-hop and single-turn vs. multi-turn, while capturing both serial and parallel execution structures. To support coherent multi-turn reasoning, we further introduce an Anchor Linkage mechanism that enforces cross-turn dependencies. Furthermore, we convert 7 public benchmarks into a unified Query--Action--Observation--Answer (QAOA) representation with fine-grained evaluation at the function-call, turn, and conversation levels. Experiments show that fine-tuning Qwen3-8B on our dataset substantially improves tool-use performance. Under the distractor-heavy Hybrid-20 setting, achieves 93.0% single-turn Strict Precision, outperforming commercial models including GPT, Gemini, and Claude.

cs.AI↗

arXiv2026

SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction

Virtual-cell models aim to predict how cell populations respond to perturbations, but control and treated cells are measured as unpaired populations, complicating the learning of perturbation-specific effects. We present SCALE, a conditional transport model that represents cells as unordered sets and predicts treated populations without cell-level matching. A shared set-aware encoder and conditional DiT backbone learn latent transport, making endpoint supervision directly delta-aligned without an auxiliary delta objective. Across genetic, chemical, developmental and immune perturbations, SCALE recovered gene-expression changes, response directions and population structure. In CRISPR data with dominant cell-line effects, SCALE outperformed competing methods across seven metrics and maintained separation among gene-target representations rather than collapsing them into a shared region. SCALE further prioritized cytokines predicted to produce distinct immune activation and inflammatory responses. Experiments using matched PBMC samples from three donors confirmed these predicted differences. Together, SCALE enables perturbation-specific prediction from unpaired populations and supports experimental prioritization.

cs.LG↗

arXiv2026

SatDL: Jointly Optimizing Data Redistribution and Training for Satellite-Based Distributed Learning

Satellite-based distributed learning promises to train machine-learning models directly in orbit using massive, globally dispersed sensor data, thereby avoiding large-scale data downloads to ground servers. However, training convergence is significantly slowed by severe non-IID data, specifically label imbalance, as each satellite observes different geographic regions with distinct labels. This imbalance extends training duration and increases energy consumption for solar-powered satellites. Existing approaches either fully redistribute data to enforce IID conditions - accelerating convergence but incurring substantial communication delays - or avoid redistribution entirely by modifying local learning algorithms to mitigate the impact of label imbalance, which, however, still prolong training and increase energy use. Both extremes result in excessive total end-to-end learning time (data-transfer delay plus training time) and thus elevated onboard energy consumption. We present SatDL, a data-redistribution framework designed to minimize total end-to-end learning time. At its core, SatDL develops a Distributor-Critic framework that jointly models and optimizes data-transfer delay and training time. Evaluations through trace-driven simulations of a 1,584-satellite Starlink constellation and hardware emulations using NVIDIA Jetson and A100 GPUs across five datasets show SatDL reduces total end-to-end learning time by up to 18.6% and onboard energy consumption by 12.23-88.00%, while maintaining inference accuracy within a few percentage points of state-of-the-art baselines.

cs.DC↗

arXiv2026

SpectraTac: A Compact Camera-Free Optical Tactile Sensor with Distributed Color Sensing

Tactile sensing is essential for physical interaction in robotics and human--machine systems. However, combining rich tactile information with compact hardware, low cost, and low computational overhead remains challenging. This work presents SpectraTac, a compact, camera-free optical tactile sensor that combines active red--green--blue (RGB) illumination with spatially distributed color sensing. Contact deforms a compliant transparent elastomer and modulates its internal light field, producing spatially differentiated changes in color and intensity. Three distributed color sensors capture these responses as low-dimensional spatio-spectral features, avoiding cameras, imaging optics, and high-dimensional image processing. The device measures 19.2 mm in diameter and 4 mm in height, with a material cost below USD~5. A data-driven decoding framework simultaneously estimates three-dimensional (3D) force and the contact region from the optical measurements. For 3D force prediction, the sensor achieved mean absolute errors (MAEs) of 0.161, 0.164, and 0.429 N along the x-, y-, and z-axes, respectively. The nine-region contact-classification accuracy was 99.9%. We further evaluated real-time 3D force tracking and contact-region-based human--machine interaction through an interactive control task. These results indicate that distributed color-resolved optical sensing offers a compact, low-cost alternative to camera-based tactile sensing for robotics, wearable sensing, and interactive systems.

cs.RO↗

arXiv2026

Zeva: In-Context Causal Learning for Generalizable Embodied Manipulation

Generalizable embodied manipulation remains difficult to achieve through pretraining alone, due to unseen physical conditions in the real world. We argue that robots need to learn from their own physical interactions on the fly during real-world deployment and use this knowledge to inform subsequent actions. We present Zeva, the first framework that enables in-context learning from a robot's own physical interaction experience while keeping the policy model frozen. Zeva employs a Causal Interaction Extractor to encode an executed action and its induced state change into a causal interaction signal, which is stored in a dual-timescale causal memory. For subsequent actions, relevant causal interaction signals are retrieved from memory and injected into the frozen policy model as context. Experiments in simulation and real-world manipulation demonstrate that Zeva achieves the best performance among the compared frontier VLAs and WAMs and, more importantly, enables self-evolution during deployment without gradient updates. Its success rate continues to improve as the robot accumulates interaction experience. Furthermore, the acquired interaction experience can generalize across tasks.

cs.RO↗

arXiv2026

LARC: Lazy Adaptive Reachability Certification of Robot Manipulator Trajectories

Discrete trajectory checks can miss collisions between sampled robot states. Reachability-based certification bounds motion between states, but uniform time partitions waste computation where clearance is large. We present lazy adaptive reachability certification (LARC), which checks a planned trajectory by bisecting only intervals with an inconclusive clearance test. For piecewise-cubic Hermite joint trajectories, the method bounds link occupancy using midpoint capsules inflated by exact componentwise speed maxima. Certified intervals covering the trajectory provide continuous-time external-obstacle clearance, subject to geometric containment, static obstacles, and a prescribed margin. On 160 AgileX PIPER trajectories from 80 start-goal pairs, LARC matched all decisions of the fixed-fine baseline at depth nine. It used 20328 interval evaluations (24.8% of baseline work), with a median paired speedup of 10.28x. A separate MoveIt/FCL audit checked 158051 states and detected collisions in 21 direct-interpolation controls, none of which LARC certified. The method reduced computation under a shared certificate model, but 27 of 139 sampled-clear trajectories remained uncertified. The sampled audit cannot independently prove continuous-time clearance.

cs.RO↗

arXiv2026

Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process

We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for each query, harnessing the collective wisdom of multiple models with diverse strengths. LLM-PeerReview is built on a novel, peer-review-inspired framework that offers a transparent and interpretable mechanism, while remaining fully unsupervised for flexible adaptability and generalization. Specifically, it operates in three stages: For scoring, we use the emerging LLM-as-a-Judge technique to evaluate each response by reusing multiple LLMs at hand; For reasoning, we can apply a straightforward averaging strategy or a principled graphical model-based truth inference algorithm to aggregate multiple scores to produce a final score for each response; Finally, the highest-scoring response is selected as the best ensemble output. LLM-PeerReview is conceptually simple and empirically powerful. Our results across four datasets show that the two variants of the proposed approach outperform the advanced model Smoothie-Global by 6.9% and 7.3% points, cross diverse task types including factual recall QA, math reasoning, and instruction following. Notably, we also establish a carefully curated benchmark suite for LLM Ensemble, integrating 12 methods across four classic datasets and three task families, all evaluated under a rigorous and consistent protocol. We hope this repository will help researchers reproduce the LLM Ensemble baselines.

cs.CL↗