SEARCH · Search arXiv

Results for “cs.DB”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

10,400 records · Page 4Linked to original sources

arXiv2026

Time-Decayed Vector Search in the Rhythm of TANGO: Jointly Modeling Semantic Similarity and Temporal Freshness

Vector search typically measures relevance through semantic similarity under a fixed scoring function. However, in a growing range of applications, relevance may evolve over time, making temporal freshness an additional signal beyond semantic similarity. In this paper, we formalize time-decayed vector search (TDVS), which incorporates continuous temporal decay into the search objective so that relevance is jointly determined by semantic similarity and temporal freshness. We design Score-Preserving Temporal Reduction (STR) that enables existing Maximum Inner Product Search indexes to directly support TDVS. We further present Chronos, a TDVS-native framework that derives an exact metric formulation and introduces Query-Orthogonal TimeLift to control data--data geometry while preserving all query--data scores and rankings. Building on Chronos, we propose TANGO, a hierarchical graph index that adopts layer-specific TimeLift geometries to preserve temporal locality at the base layer while strengthening long-range semantic connectivity in upper layers. TANGO traverses the hierarchy using the exact TDVS score, caches temporal factors to reduce computation, and supports efficient online insertion. Extensive experiments show that TANGO achieves up to 3.5$\times$ higher query throughput and 4.05$\times$ faster index construction than state-of-the-art graph-based competitors. TANGO also maintains its advantage over all competitors across diverse temporal settings and enables efficient online insertion, demonstrating its robustness and practicality.

cs.DB↗

arXiv2026

Compiling Linear Datalog to SQL for Program Analysis

Datalog is a declarative query language that has proven highly effective for expressing static program analyses. Although Datalog has deep roots in database theory, most recent advances have largely emerged from the programming languages and compiler communities, with systems such as Soufflé. In contrast, modern relational engines have made significant progress in optimizing recursive SQL. This paper revisits the connection between Datalog and relational databases, advocating recursive SQL as a backend for Datalog evaluation. We present a compilation framework that translates Datalog programs, particularly those in the Linear Datalog fragment, into equivalent recursive SQL queries. To bridge the gap between Datalog and SQL, the compiler routes every program through an intermediate language called Midlog. The compiler additionally recovers functional dependencies from the program and exposes them as schema keys, unlocking the engine's standard query optimizations. This approach enables existing database engines to execute a broad class of program analyses, outperforming the Soufflé engine by up to an order of magnitude on the Umbra backend. Umbra achieves a geometric-mean speedup of 5.46$\times$ at 8 threads, whereas DuckDB is competitive with Soufflé single-threaded and is slower at 8 threads (geometric-mean speedup of 0.68$\times$). Furthermore, the generated SQL is portable; it runs on seven database systems without any engine modification. Our results highlight what the relational engines require to fully support Datalog for large-scale program analysis.

cs.DB↗

arXiv2026

Large-scale spatial variable gene atlas for spatial transcriptomics

Spatial variable genes (SVGs) reveal critical information about tissue architecture, cellular interactions, and disease microenvironments. As spatial transcriptomics (ST) technologies proliferate, accurately identifying SVGs across diverse platforms, tissue types, and disease contexts has become both a major opportunity and a significant computational challenge. Here, we present a comprehensive benchmarking study of 20 state-of-the-art SVG detection methods using human slides from STimage-1K4M, a large-scale resource of ST data comprising 662 slides from more than 18 tissue types. We evaluate each method across a range of biologically and technically meaningful criteria, including recovery of pathologist-annotated domain-specific markers, cross-slide reproducibility, scalability to high-resolution data, and robustness to technical variation. Our results reveal marked differences in performance depending on tissue type, spatial resolution, and study design. Beyond benchmarking, we construct the first cross-tissue atlas of SVGs, enabling comparative analysis of spatial gene programs across cancer and normal tissues. We observe similarities between pairs of tissues that reflect developmental and functional relationships, such as high overlap between thymus and lymph node, and uncover spatial gene programs associated with metastasis, immune infiltration, and tissue-of-origin identity in cancer. Together, our work defines a framework for evaluating and interpreting spatial gene expression and establishes a reference resource for the ST community.

stat.AP↗

arXiv2026

SINDI: An Efficient Index for Sparse Vector Approximate Maximum Inner Product Search

Sparse vector Maximum Inner Product Search (MIPS) is crucial in multi-path retrieval for Retrieval-Augmented Generation (RAG). Recent inverted index-based and graph-based algorithms have achieved high search accuracy with practical efficiency. However, their performance in production environments is often limited by redundant distance computations and frequent random memory accesses. Furthermore, the compressed storage format of sparse vectors hinders the use of SIMD acceleration. In this paper, we propose the sparse inverted non-redundant distance index (SINDI), which incorporates three key optimizations: (i) Efficient Inner Product Computation: SINDI leverages SIMD acceleration and eliminates redundant identifier lookups, enabling batched inner product computation; (ii) Memory-Friendly Design: SINDI replaces random memory accesses to original vectors with sequential accesses to inverted lists, substantially reducing memory-bound latency. (iii) Vector Pruning: SINDI retains only the high-magnitude non-zero entries of vectors, improving query throughput while maintaining accuracy. We evaluate SINDI on multiple real-world datasets. Experimental results show that SINDI achieves state-of-the-art performance across datasets of varying scales, languages, and models. On the MsMarco dataset, when Recall@50 exceeds 99%, SINDI delivers single-thread query-per-second (QPS) improvements ranging from 4.2 to 26.4 times compared with SEISMIC and PyANNs. Notably, SINDI has been integrated into Ant Group's open-source vector search library, VSAG.

cs.DB↗

arXiv2026

VeriTS: Verifiable Model-Enhanced Time-Series Queries on Blockchain Systems

Blockchain data is temporal. Every transaction carries a timestamp and the chain imposes a total order, so on-chain data forms per-source time-series streams. However, existing systems support only basic lookups on blocks and transactions, and cannot answer time-series queries such as time-range retrieval and windowed aggregation. Offloading queries off-chain restores expressiveness, but the off-chain query layer is untrusted, so results must be verifiable. To this end, we propose VeriTS, the first verifiable time-series query framework for blockchain systems. It supports efficient range and aggregation queries without altering blockchain storage structures. VeriTS maintains an off-chain query layer that represents each stream through an authenticated aggregate interval tree. The tree serves as the query index and as the authenticated data structure at once, so a windowed aggregate is answered by folding a logarithmic number of node aggregates. VeriTS verifies completeness through a minimum covering set and soundness through aggregate folding. It extends both guarantees to an approximate path over model segments, redefining completeness and soundness under bounded error. Miners validate a model's residual rather than replay its computation, so even an adversarial encoder can inflate proof size and answer width but never correctness. Experiments offer evidence that on windowed aggregation, VeriTS improves verification efficiency by more than two orders of magnitude over per-record proofs. Range-query proofs shrink by up to 14.5x.

cs.DB↗

arXiv2026

MARR: Decoupling Policy, Execution, and Calibration for All-in-One Medical Image Restoration

All-in-one medical image restoration seeks to recover heterogeneous clinical images with a single model, but PET, CT, and MRI differ substantially in degradation statistics, anatomical contrast, and output-space bias. A fully shared network can entangle modality-specific residual errors, whereas separate modality-specific networks sacrifice the practical advantages of unified deployment. We therefore recast all-in-one restoration as a question of where limited adaptation should be placed: policy selection, feature execution, or output calibration. We propose MARR, a compact restoration framework that constrains multi-modality adaptation into degradation-aware policy routing, modality-private residual execution, and image-domain residual correction without requiring degradation labels or separate modality-specific models. The policy branch forms a routing prompt from input statistics, latent content, and modality identity, and uses it only as a control signal. Prompt-gated modality-private adapters then perform lightweight residual refinement at intermediate decoder stages, while zero-initialized modality-specific output heads calibrate the final image-domain residual without perturbing the initial shared prediction. On an all-in-one PET, CT, and MRI restoration benchmark, MARR outperforms thirteen methods re-trained under the same protocol, achieving PSNR values of 37.34 dB, 33.85 dB, and 32.09 dB on PET, CT, and MRI, respectively, and the best modality-average PSNR of 34.43 dB. The code is publicly available at https://github.com/CHB-learner/MARR.

cs.CV↗

arXiv2026

SmartANN: Object Causal Modeling Boosts Approximate Nearest Neighbor Diagnosis and Auto-Design

Approximate Nearest Neighbor (ANN) algorithms achieve high efficiency through interdependent phases across index construction and query execution. This coupling allows upstream performance loss to propagate downstream, affecting execution behavior and measurable outputs. Existing component-level analyses mainly compare isolated design choices, while end-to-end benchmarks report aggregate metrics; neither traces loss propagation across dependent phases, hindering root-cause attribution and automated redesign. We present SmartANN, a framework based on the object causal model (OCM) for ANN bottleneck attribution and automated redesign. SmartANN represents an ANN workflow as eight ordered, replaceable objects and diagnoses them with a sequential diagnose-and-replace loop. At each iteration, it identifies the first object deviating from expected behavior or output as a bottleneck. Because an upstream bottleneck can obscure downstream ones, SmartANN replaces it with a test oracle when available, or with an implementation producing a better outcome, then continues downstream diagnosis. From the diagnosed bottlenecks and failure causes, SmartANN composes compatible actions from a pluggable action library to generate an optimized end-to-end ANN design. We instantiate SmartANN for IVF-PQ and HNSW, covering partition-and-quantization and graph-based ANN families. Experiments on eight real-world datasets show that SmartANN improves Recall by 0.24--74.20%, and increases QPS by 28.8--256.5% at comparable Recall, with low diagnosis and auto-design overhead. The code is available at https://github.com/zhouyutong20/SmartANN.

cs.DB↗

arXiv2026

X-DigCheck: Co-Evolving Application Profiles and Knowledge Graphs, Demonstrated on the RTI Documentation of Rupe Magna

We demonstrate X-DigCheck, a domain-independent environment for building and maintaining application profiles as they co-evolve with the data they describe. Profiles developed against a fixed ontology quickly drift from the schema they were meant to capture. X-DigCheck treats profile construction as a continuous ontology-data co-evolution loop: data are lifted into RDF against the profile, checked through competency questions and SHACL, and the resulting reports jointly drive revisions of the ontology, mappings, constraints, and graph. The loop is agnostic to the domain and to the pipeline that produces the graph. We validate and demonstrate the tool in the cultural heritage domain, on the construction of RupeMagna-RTI, the first Reflectance Transformation Imaging (RTI) specialisation of the Cultural Heritage Survey ODP (CHS-ODP), aligned with CIDOC-CRM/CRMdig, ArCo, CHAD-KG, and Getty AAT, with semRTI as the lifting pipeline of this use case. The demonstration lets visitors run one full turn of the loop -on the shipped Rupe Magna (Grosio, Italy) RTI survey, or on a profile and graph of their own -executing the competency-question and SHACL checks live and reading the bidirectional coverage report that flags modelling gaps and stale assumptions. The result is a portable co-evolution environment for profile engineering, together with a reusable RTI application profile produced through it. A screencast of the demonstration is available at https://zenodo.org/records/22210609.

cs.DB↗

arXiv2026

Property Testing for Recursive Query Languages

In the context of database querying, property testing provides a framework for testing query answers with high confidence while inspecting only a sublinear part of the database, through completion queries and size queries. A fundamental result of Chen and Yoshida (2019) states that non-satisfaction of a Boolean conjunctive query $q$ is testable with a constant number of such queries and one-sided error if and only if $q$ is equivalent to an $α$-acyclic query. In this article, we initiate the study of property testing for recursive query languages, focusing on two-way regular path queries (2RPQs) and monadic Datalog. One of our main results is positive: non-answers to any 2RPQ are constant query testable with one-sided error. We extend this slightly to a certain class of monadic Datalog programs in which recursion is restricted to be linear and rule bodies must be $α$-acyclic. Turning towards unrestricted monadic Datalog, we next show that if a monadic Datalog program $Π$ is not equivalent to an $α$-acyclic program, then falsity of $Π$ is not constant query testable with one-sided error. This is under the assumption that all rule-bodies are self-join free. We leave open the case of monadic Datalog programs with $α$-acyclic rule bodies that are not restricted to linear recursion, but observe as a first step that there exist $α$-acyclic programs that are mildly non-linear and constant query testable with one-sided error.

cs.DB↗

arXiv2026

Aker: Density-Aware Approximate Caching for Vector Search (Extended Version)

Disk-based approximate nearest neighbor search (ANNS) incurs high I/O overhead due to frequent disk accesses during index traversal. Approximate caching, which reuses the results of past queries to serve future similar queries, offers a promising approach to bypass expensive disk searches. However, existing approaches suffer from two key limitations. First, their approximate hit predicates fail to simultaneously achieve high throughput and high accuracy, as they do not adapt to the varying local neighbor density in high-dimensional spaces. Second, they lack an effective refresh mechanism to maintain cache correctness under vector updates. We present Aker, an approximate cache for disk-based ANNS. Aker addresses these limitations through two core design choices. First, we introduce a per-query similarity threshold, where each cache entry maintains its own threshold that is dynamically adjusted based on observed cache hit patterns. This design enables Aker to adapt to neighborhood densities to preserve both efficiency and accuracy. Second, we propose del-consistency, a consistency model for ANNS caches that applies deletions eagerly and insertions lazily. Under this model, Aker implements a low-overhead refresh mechanism that bounds cache staleness and preserves high search accuracy. We integrate Aker into pgvector and evaluate it on representative workloads. Aker improves recall by up to 64 percentage points over prior solutions and increases QPS by up to 3.2x, while using 0.6x the memory of pgvector's shared buffers.

cs.DB↗

arXiv2026

XVAE-WMT: Explainable Wavelet-Temporal Variational Autoencoder for Blind Source Separation of Heart and Lung Sounds

The separation of cardiovascular sounds is a critical task in biomedical signal processing. In this paper, we introduce XVAE-WMT1, an unsupervised explainable generative AI algorithm combining a variational autoencoder (VAE) with explainable AI (XAI), wavelet-based inputs, a post-hoc output mask, and temporal consistency (TC) loss. Unlike existing supervised and VAE-based methods that rely on Short-Time Fourier Transform (STFT) and ignore latent interpretability, XVAE-WMT requires no paired clean recordings and integrates a Continuous Wavelet Transform (CWT) front-end for superior time-frequency localization. We assessed the latent space interpretability via different metrics, with SHAP (SHapley Additive exPlanations) enabling dimensionality reduction to the top 75% of latent features while preserving separation quality. Evaluated across two datasets using Signal-to-Distortion Ratio (SDR), Signal-to-Interference Ratio (SIR), and Signal-to-Artifacts Ratio (SAR), XVAE-WMT attains 26.8 dB SDR, 32.8 dB SIR, and 28.6 dB SAR.

cs.SD↗

arXiv2026

ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language

Large language models (LLMs) have shown strong potential for translating natural-language (NL) requirements into PL/SQL programs, attracting increasing attention from the database community. However, existing NL-to-PL/SQL efforts primarily focus on directly generating PL/SQL from complete NL requirements. In practice, PL/SQL development involves diverse scenarios, such as from-scratch development, code modification, debugging, and optimization, and may require either direct generation or multi-turn interaction. Yet, no comprehensive benchmark evaluates multi-scenario, direct and interactive, and multi-dialect NL-to-PL/SQL development. In this paper, we present ProcArena, an execution-based benchmark covering both Direct and Interactive modes. ProcArena comprises 3,998 executable tasks over 157 databases, spanning nine development subscenarios in PostgreSQL and Oracle. We construct challenging Direct tasks through Iterative Logic Enhancement and scenario-specific adapters, and derive paired Interactive tasks through Knowledge Integration and Requirement Perturbation while preserving executable targets. We further design a controlled Solver-User Simulator protocol that allows models to clarify user intent and inspect the database environment without exposing hidden execution feedback. Evaluating seven language models, we find that the best average scores are only 62.2% and 57.8% in Direct and Interactive, respectively, demonstrating that realistic NL-to-PL/SQL development remains challenging, particularly in interactive settings.

cs.CL↗

arXiv2026

MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing

Memory is a fundamental component for long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, many stateful systems retain sequential autoregressive extraction or state-dependent maintenance on the write path, delaying when new evidence becomes queryable. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data-management problem. MemForest breaks the sequential bottleneck via parallel extraction, decoupling memory construction into concurrent, independent operations. We further introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees and replaces global rewrites with localized dirty-path refresh. Dirty summaries can be refreshed in parallel across nodes and trees. End-to-end work remains proportional to incoming content; the logarithmic bound applies only to structural insertion and level-dependent refresh depth in balanced trees. We evaluate MemForest on two long-context benchmarks, LongMemEval-S and LoCoMo. Experiments use Qwen3-4B, Qwen3-30B, and Gemma-4-12B-IT. With Qwen3-30B, MemForest reaches 81.8 percent pass at 1 on LongMemEval-S, while its input-normalized build rate is 6.0 times that of EverMemOS. On LoCoMo categories 1 to 4, it reaches 84.09 percent, within 0.13 percentage points of EverMemOS; on a matched conversation, its build rate is 9.5 times higher. These results show that MemForest reduces memory-freshness latency while retaining strong answer quality.

cs.DB↗

arXiv2026

Does SRL Pave the Road to Explainable Reasoning? Lessons Learned from an Implementer's Perspective

The Shape Rules Language (SRL) Working Draft defines how to derive new RDF triples from an RDF graph using inference rules. Each rule matches graph patterns and instantiates triple templates whose output feeds into validation pipelines, SPARQL queries, or further inference. RDF reasoning has traditionally relied on fixed entailment regimes (RDFS, OWL), rule-based ad-hoc languages such as N3, or other implementation-specific solutions without a shared standard. SRL introduces user-defined production rules with a defined grammar, dependency analysis, execution ordering, and termination guarantees. However, no authoritative implementation exists, leaving practitioners with little guidance on how to build a conformant engine or on what problems the language can solve. We implemented two SRL engines and evaluated both on classical RDF reasoning tasks for soundness, completeness, and speed. The first reuses an existing SPARQL query engine and its query parser; the second is a dedicated engine. The SPARQL-based engine reused an existing modular parser for query construction and SPARQL CONSTRUCT for triple production, reducing engine-specific work. The dedicated engine was two to six times faster, the gap widening as rule sets grow. Both engines were validated against the SRL conformance test suite, supplemented by additional use-case-driven tests. A usable SRL engine can be built inexpensively on top of a SPARQL engine, with a moderate speed trade-off that a dedicated implementation recovers. Despite the specification's immaturity, the language already supports practically useful reasoning tasks.

cs.DB↗

arXiv2026

RUBICON: Agentic AI for Messy Enterprise Data

Enterprise data exists in many forms, such as tables, text, maps, e-mail, and CAD models, that are access-controlled and hidden behind bespoke interfaces. Current agentic AI systems delegate the entire query workflow to a frontier LLM: a single model interprets the request, selects sources or tools, integrates retrieved evidence, judges completeness, and generates an answer, with few constraints, limited use of schemas, and text as the primary representation throughout. We argue that this is an ineffective abstraction for enterprise data. Reliable agentic AI should instead require structure: a constrained query interface over each source and a table-centric integration layer driven by a query processor. We introduce RUBICON, a system that embodies this vision. RUBICON is based on two observations. First, text-to-SQL fails on real enterprise data and must be dramatically subsetted to achieve reliable results. Second, data integration across disparate corporate datasets is best performed using tables as the core abstraction rather than text-centric LLM pipelines. We evaluate RUBICON on two benchmarks: our enterprise-focused RUBICON-Bench, against agentic baselines, and SemBench, against LOTUS and Palimpzest. On RUBICON-Bench, where queries require coordination across heterogeneous enterprise sources, RUBICON achieves 100% end-to-end accuracy, while all agentic baselines, including single- and multi-agent ReAct systems, produce no correct answers. On SemBench, RUBICON surpasses both LOTUS and Palimpzest: it achieves 14.7% higher accuracy, reduces latency by 62.64%, and lowers token cost by 98.64%, demonstrating that a table-centric architecture better matches enterprise data while yielding significant efficiency gains.

cs.DB↗

arXiv2026

Bounded, Indeterminate, or a Bug: A Condition-Aware Oracle for Differential Testing of SQL Aggregates

Differential database testing compares results across engines and calls a discrepancy a bug. For floating-point aggregates this is unsound: engines legitimately disagree because floating-point arithmetic is not associative. Practice patches this with an epsilon; the leading oracles avoid floating point entirely. We give the oracle this practice lacks, and show its decisive quantity is not the query but the engine's algorithm. Ground truth is the exact rational value of the stored doubles -- arithmetic, not another engine -- and each discrepancy is classified exact, bounded, or indeterminate. The relative error of an aggregate f under an algorithm A obeys rel_err <= C_A(n,u) * kappa_f^p, so the testability boundary, beyond which no oracle can separate a bug from rounding, is kappa*_{f,A} = (1/C_A)^{1/p}. SUM and AVG are the linear case p=1; variance is p=2 for the one-pass algorithm and p=1 for Welford. Across eight engines in four classes the measured exponent recovers each algorithm, and ClickHouse is the lone one-pass engine (p=2.05); engine-wide, it returns zero standard deviation, NaN correlation and wrong-sign regression, while every other engine stays exact and the vendor ships the Welford fix. Its variance is untestable at a condition number 10^6 below SUM's, which ordinary storage conventions (epoch-nanosecond timestamps, tight sensors) cross -- there ClickHouse errs by 2100%. A randomised hunt of 360 tests finds zero anomalies, evidence the oracle is sound. Code and data are public.

cs.DB↗

arXiv2026

Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent

Descriptive scientific metadata in public repositories are often incomplete and inconsistent with community standards and ontologies, limiting data FAIRness. Large language models (LLMs) offer a promising approach to automatically standardizing such metadata when provided with relevant standards in machine-actionable form, such as metadata templates from the CEDAR Workbench. Prompt engineering, however, provides only fixed snapshots of these standards and relies on an LLM's pretrained knowledge to interpret and satisfy their constraints. We evaluate whether giving an LLM access to metadata specifications and authoritative terminology at runtime improves automated metadata standardization. Methods: We present ARMS, a tool-augmented LLM agent that retrieves complete CEDAR metadata templates and dynamically queries authoritative biomedical terminology services at execution time. We compared ARMS with a prompt-based approach on 839 legacy metadata records from the Human BioMolecular Atlas Program (HuBMAP), using expert-standardized records as the reference standard. Results: ARMS outperformed the prompt-based approach, increasing precision from 0.56 to 0.93 and recall from 0.51 to 0.85, with improvements across all field categories and assay types. The largest gains occurred for ontology-constrained fields, where precision increased from 0.36 to 0.92. Conclusion: LLMs cannot convert legacy metadata to standards-adherent form without knowledge of the relevant standards. ARMS improves metadata standardization by providing runtime access to authoritative resources that define valid metadata. Machine-actionable metadata standards enhance LLM-based rectification of legacy metadata, especially when they can be queried dynamically.

cs.DB↗

arXiv2026

One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows

Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Yet completing consequential work beyond code requires more than producing a plausible response or valid tool call: agents must gather missing information over multiple turns, follow domain policies, coordinate dependent tools, and realize the correct persistent state transition without collateral effects. In this paper, we introduce Thinkingbox, a sandbox for tool-agent-user interaction that provides isolated MCP-compatible tool sessions, complete execution traces, and outcome evaluation over terminal backend state. Built on this sandbox, Thinkingbox-bench contains 507 policy-conditioned workflows across numerous scenarios, including retail, hospitality, auto insurance, neobank internal IT, and consulting IT/HR support. Each attempt is evaluated by task-specific executable checks that accept valid trajectories while rejecting wrong, missing, or extra effects; designated tasks additionally check required properties of the final response. Across proprietary and open-weight models, the strongest model Claude Opus 5 achieves 66.50% pass@1, but only 47.53% pass^20. Moreover, many failed trials show clean termination and valid state-changing actions, showing that response or tool-call-level signals are not clear proxies for end-to-end task completion. Thinkingbox-bench reveals a large gap between occasionally finding a successful trajectory and reliably completing stateful business tasks. We release both Thinkingbox and Thinkingbox-Bench: https://github.com/microsoft/thinkingbox

cs.CL↗