Search: “KOPA-Bench”

30 stories

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

SeverityAll critical 0 high 0 medium 0 low 0 info 1

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe

Researchers introduce KOPA-Bench, a 145-task Korean public API tool-calling benchmark, and EDGE, an execution-grounded data synthesis method.

An arXiv paper presents KOPA-Bench, a benchmark of 145 real-world tasks chaining multiple tool-calls across live Korean government APIs, motivated by data-sovereignty requirements for on-premise open-source LLM agents. It also introduces EDGE, an execution-grounded dynamic graph that keeps only tool-output-to-input links verified by live API calls before synthesizing executable multi-step trajectories. A 9B model fine-tuned with GRPO on the resulting dataset nearly matches its untuned 27B family sibling on KOPA-Bench and improves on the BFCL benchmark.

arXiv cs.AI / cs.LG / cs.CLSep 4, 17:44 UTC · 11d agoAI research1

K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations

Clinician-calibrated K-Bench evaluates 125 LLM configurations on 200 high-risk mental health vignettes, exposing wide variation in suicide and violence risk handling.

K-Bench is a clinician-calibrated, protected benchmark evaluating 125 model configurations from 33 base models across 14 providers on 200 multi-turn vignettes covering suicide, self-harm, domestic violence, substance misuse and no-risk presentations. A frozen GPT-4o judge achieved 94.2% exact agreement with clinician consensus across 6,751 eligible comparisons from 151 clinician-rated transcripts. Leading models combined supportive conversation with combined-risk scores above 95, while risk exploration varied substantially among weaker configurations; therapeutic prompting helped weaker models and elevated reasoning produced no average improvement. A continuously updated public leaderboard is hosted at k-bench.ai with protected test materials.

arXiv cs.AI / cs.LG / cs.CLSep 14, 16:49 UTC · 1d agoAI safety & security

‘Now We Can Know Everything and Do Anything,’ Jensen Huang Says at Dreamforce

Salesforce unveiled Koa, its first CRM reasoning model post-trained on NVIDIA Nemotron 3 Super, announced during Jensen Huang's Dreamforce keynote.

At Salesforce Dreamforce, NVIDIA CEO Jensen Huang joined Marc Benioff onstage as Salesforce announced Koa, its first CRM reasoning model, post-trained from NVIDIA Nemotron 3 Super using NeMo RL, NeMo Gym, and NeMo AutoModel. Koa was fine-tuned on a proprietary synthetic dataset drawn from nearly three decades of enterprise CRM deployments across 14+ industries, with no customer data used in training or inference. On Salesforce's CRM Bench of real-world tasks, Koa matches or exceeds leading model performance on CRM actions with 3x fewer errors. Koa already powers an employee agent in Slack, enters customer pilots in October with Formula 1, UChicago Medicine, Baxter Credit Union, 1-800Accountant, Engine, and Xero, and reaches general availability in Winter 2026 in U.S. regions.

NVIDIA BlogSep 15, 22:24 UTC · 17h agoAI industry

Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models

Researchers introduce KoNA, a benchmark exposing vision-language models' failures at selective non-compliance, plus fine-tuning that improves refusal and abstention accuracy.

KoNA is a benchmark for evaluating selective non-compliance in vision-language models across five categories: False Premise, Visual Inaccessibility, Universal Unknown, Task Feasibility and Safety. It tests both query-level and component-level non-compliance using paired single and compound queries, and evaluations across diverse VLMs show models often fail to refuse, correct or abstain appropriately, with failures worsening on compound queries. Fine-tuning VLMs on KoNA examples substantially improves non-compliance accuracy while largely maintaining performance on fully answerable tasks.

Hugging Face daily papersSep 3, 20:00 UTC · 12d agoAI research1

Salesforce and Nvidia’s new reasoning model is everything the AI labs should fear

Salesforce and Nvidia launch Koa, Salesforce's first reasoning model, built on Nvidia's open-weight Nemotron and post-trained on synthetic sales and support data.

Salesforce announced Koa at Dreamforce, its first reasoning model, built on Nvidia's open-weight Nemotron and post-trained with synthetic data mimicking sales and customer-support scenarios rather than real customer data. Koa will be offered through the Agentforce platform's AI gateway as a cheaper, token-efficient alternative to closed frontier models like Claude and ChatGPT for enterprise tasks. Salesforce simultaneously announced a ClaudeForce partnership with Anthropic keeping customer data inside Salesforce's infrastructure.

TechCrunch · AISep 15, 12:00 UTC · 1d agoModel release1

MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant

MP-Bench is the first benchmark for voice agents in multiparty conversations, finding real-time agents near chance on turn-taking.

MP-Bench is the first benchmark designed to objectively evaluate conversational speech systems as active participants in multi-party conversations. It assesses agents on turn-taking awareness and response appropriateness, with comprehension-based question-answering as a complementary evaluation. Benchmarking 12 voice agents shows real-time agents score at or below 22% on multiparty comprehension and remain near chance on multiparty turn-taking.

arXiv cs.AI / cs.LG / cs.CLSep 11, 17:11 UTC · 4d agoAI research2

RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?

RoboSPA introduces a 527K-trajectory benchmark with 280 task variants showing current VLA models struggle with spatial reasoning and long-horizon planning.

RoboSPA is a large-scale robotic manipulation dataset and benchmark for diagnosing embodied reasoning in vision-language-action models, covering fine-grained spatial reasoning and long-horizon procedural planning. It spans 10 task categories and 56 base tasks instantiated across five difficulty levels for 280 variants, with 527K trajectories collected across multiple embodiments and diverse scenes. Diagnostic metrics go beyond binary success rates, and experiments show current VLA models struggle with complex spatial relations, precise low-level execution, and memory-intensive planning.

Hugging Face daily papersSep 3, 20:00 UTC · 12d agoAI research

RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?

RoboSPA introduces a 527K-trajectory robotic benchmark with 280 task variants exposing VLA model weaknesses in spatial reasoning and long-horizon planning.

RoboSPA is a large-scale robotic manipulation dataset and benchmark for diagnosing embodied reasoning in vision-language-action models, spanning fine-grained spatial reasoning and long-horizon procedural planning. It covers 10 task categories and 56 base tasks instantiated across five difficulty levels for 280 variants, with 527K trajectories collected across multiple embodiments. Experiments on representative VLA models show current systems struggle with complex spatial relations, precise low-level execution, and memory-intensive planning.

arXiv cs.AI / cs.LG / cs.CLSep 4, 16:19 UTC · 11d agoAI research

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

VDiff-Bench, a 1,756-question benchmark, shows multimodal LLMs struggle with fine-grained image-difference identification, scoring as low as 8.7% on low-level changes.

VDiff-Bench is a multiple-choice benchmark of 1,756 four-way questions over image pairs covering 10 change categories including position, motion, color, texture, OCR/text and illumination, with curated hard negatives. Evaluation of 11 state-of-the-art open- and closed-source MLLMs shows fine-grained visual comparison remains brittle: 7-8B-scale open-source models score 52.5-70.6% on semantic changes but only 8.7-33.3% on low-level changes like noise and texture. Notably, Grok 4.3 shows a sharp performance drop on noise and texture differences, falling behind large open-source models like Kimi K2.5 and K3.

Hugging Face daily papersSep 4, 20:00 UTC · 11d agoAI research

Kaininja: Extending Native 3D Generators to the Part Level

KaiNinja extends TRELLIS.2 native 3D generation to part-level assets via a dual-volume O-Voxel representation, cutting whole-object Chamfer distance by 40%.

KaiNinja extends the TRELLIS.2 native 3D generator to produce part-level assets instead of one fused mesh, enabling downstream editing, rigging, and simulation. A dual-volume form of the O-Voxel representation solves the problem that a single volume cannot represent interfaces where two parts touch. The model needs no segmentation network, is partly trained on LLM-agent-authored part data, lowers whole-object Chamfer distance by 40%, and raises strict part F-score by 16% versus other part-generation pipelines.

Hugging Face daily papersSep 13, 20:00 UTC · 2d agoAI research

Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs

A GitHub project streams Moonshot's 2.8T-parameter Kimi K3 from four SSDs to run at 1 token/s on a MacBook Pro.

A GitHub repository (argonautlabsai/deltafin) demonstrates running Moonshot AI's Kimi K3, a 2.8-trillion-parameter model, on a MacBook Pro by streaming its weights from four SSDs at 1 token per second. The project drew 55 points and 22 comments on Hacker News, highlighting consumer-hardware inference for extremely large models.

Hacker News · AISep 8, 20:07 UTC · 7d agoAI tools & infra HN 55↑ · 22 comments

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

MetroLLM-Bench is a 955-case benchmark testing language models as transit kiosk tool-calling runtimes across six real metro systems.

The benchmark covers 37-414-station metro systems and eleven task categories including routing, fare calculation, disruptions, accessibility, and adversarial input, with 14 deterministic and 8 semantic scoring components. Of 26 models from six vendors, a PEFT-tuned 4B Qwen 3.5 student scored 91.3 on Tier 1, exceeding GPT-5.6 (90.6/90.0), while Muse Glimmer 30B led the composite ranking. A deterministic rule-based baseline reached 84.6, and PEFT gains over base models shrank from +7.03 points at 2B to -0.91 at 27B.

Hugging Face daily papersSep 8, 20:00 UTC · 7d agoAI research

RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems

Researchers introduce RESCUE-Bench, a video benchmark of 191 couple and family conversations evaluating LLMs on relation-aware multi-party emotional support.

RESCUE-Bench is built from real couple and family interview conversations, containing 191 samples, 7,079 annotated turns, and 1,064.8 minutes of video. It defines six tasks measuring two capabilities: Relational Understanding and Relation-Sensitive Support. Experiments with ten LLMs show models handle local emotional cues but struggle with relation pattern prediction, viewpoint prediction, and support strategy prediction.

Hugging Face daily papersSep 8, 20:00 UTC · 7d agoAI research

Notes on gotchas while migrating 35kb preprompts from Opus to self-hosted Ollama

Opinion piece urges migrating 35KB preprompts from Anthropic/OpenAI to self-hosted Ollama, citing session privacy risks and safety filters blocking security research.

The author documents gotchas migrating 35KB preprompts from Claude Opus to self-hosted Ollama, motivated by fears that frontier providers train on user sessions, citing the OpenAI Navier-Stokes controversy. The piece argues inference providers cannot audit their own retention or training pipelines and that only self-hosted hardware offers verifiable privacy. It also criticizes frontier safety filters for refusing vulnerability research tasks and calls for models that support exploitability testing in CI/CD pipelines.

Hacker News · AISep 14, 13:59 UTC · 2d agoAI industry HN 41↑ · 13 comments1

PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift

PIDS-Bench shows prompt-injection detectors scoring F1 above 0.98 still misclassify about one-third of external benign security-adjacent prompts, revealing provenance-sensitive over-defense.

PIDS-Bench is a frozen multi-axis benchmark that jointly evaluates prompt-injection detectors on attack detection and benign false-positive behavior at fixed thresholds, spanning in-distribution inputs, hard-benign prompts, obfuscated attacks, and domain/structural distribution shifts. It evaluates seven detectors plus a rule-based lower-bound reference. A detector exceeding F1 = 0.98 on held-out data still misclassifies roughly one-third of an externally-sourced benign security-adjacent subset, and no internal detector reaches F1 >= 0.95 with hard-benign FPR <= 0.10 on the stress distribution. Hard-negative augmentation nearly eliminates over-defense on curated stress inputs but leaves it intact on externally-sourced prompts, a pattern termed provenance-sensitive over-defense.

arXiv cs.CRSep 14, 04:28 UTC · 2d agoAI safety & security

GPT-6 Astra appears to show a "step change" in spatial reasoning based on early benchmarks

Early StationeryBench robotics results show OpenAI's GPT-6 Astra far ahead of Ai2's MolmoAct2 at dual-arm manipulation, completing 7 of 100 tasks versus zero.

A new robotics benchmark called StationeryBench tested OpenAI's GPT-6 Astra against Ai2's MolmoAct2 on five desk-object tasks using identical dual-arm YAM robots over 200 trials. Astra fully completed 7 of 100 tasks with a median progress score of 46 out of 100, while MolmoAct2 completed zero with a median score of 12. Cornell and Google DeepMind researcher Yoav Artzi called the result a 'step change in spatial reasoning' and noted Astra approaches human-level accuracy on the unpublished REMAP benchmark. He speculated OpenAI trained the model on large amounts of 3D data such as Blender scenes, and OpenAI reportedly plans consumer robots.

The DecoderSep 12, 14:26 UTC · 4d agoAI industry 2 sources1

Measuring benchmark optimization in speech recognition

Hugging Face examines how much speech recognition systems overfit benchmarks and how to measure benchmark optimization in ASR.

A Hugging Face post on measuring benchmark optimization in automatic speech recognition, analyzing how model improvements on benchmarks reflect genuine capability gains versus overfitting. It is evaluation methodology research with no direct security impact.

Hugging Face BlogAug 21, 00:00 UTC · 26d agoAI research

ECHO: A Matched-Contrast Benchmark for Context-Sensitive Turn-Taking in Full-Duplex Dialogue

ECHO benchmark pairs identical-overlap Chinese dialogue examples with contrasting contexts, revealing most full-duplex systems bias toward yielding the floor.

ECHO is a paired diagnostic benchmark for Chinese full-duplex turn-taking that matches examples with identical overlap transcripts but contrasting preceding multi-turn contexts, one requiring Yield and the other Keep. It also includes off-talk examples for diagnosing unnecessary yielding and introduces pair accuracy, which grants no credit to constant-action policies. Experiments across multiple full-duplex systems show most exhibit a pronounced Yield bias, performing substantially better on interruptions than backchannels. The benchmark and metadata will be publicly released.

arXiv cs.AI / cs.LG / cs.CLSep 15, 15:58 UTC · 23h agoAI research

τ^τ-Bench: An Environment for End-To-End, Realistic Agent Construction

New τ^τ-bench tasks coding agents with building deployable customer-service agents; best config, Claude Opus 5, passes only 23.9% of simulations.

Researchers introduce τ^τ-bench, an end-to-end benchmark where a developer agent must build a complete customer-service agent from real business records, a client with requirements, a production API, an inherited codebase, and cost/model limits, then is scored by deploying it against held-out simulated users. Across 53 tasks in four domains, the strongest configuration, Claude Opus 5 under Claude Code, passes just 23.9% of evaluation simulations versus an 82.2% expert-authored reference ceiling. Failure modes mirror those of human developers: shallow queries instead of deep record comprehension, almost no client communication, and shipping the first architecture that runs rather than experimenting.

Hugging Face daily papersSep 3, 20:00 UTC · 12d agoAI research

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

E2A-Bench, a 969-query financial chart reasoning benchmark, finds VLMs fail evidence-to-action consistency, with fine-tuning amplifying BUY:SELL bias 4-6x.

E2A-Bench is a 969-query benchmark built from 323 HS300 constituents across three input modalities with deterministic OHLCV-derived evidence anchors, evaluating grounding, reasoning-action consistency, evidence-confidence calibration, and directional coverage via UCR, RCI, ECI, and NDR metrics. Testing 20 VLMs showed the lowest-hallucination model ranked near the bottom on coverage with only 6.4% directional coverage, and oracle-aided verification reduced unsupported claims but could collapse coverage. Financial fine-tuning amplified the BUY:SELL ratio by factors of 4.21 to 4.68 across base-fine-tuned pairs.

Hugging Face daily papersSep 12, 20:00 UTC · 3d agoAI research

GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting

GoDeep achieves annotation-free open-vocabulary 3D segmentation by grounding structured image descriptions in language-only embeddings, outperforming CLIP-based lifting on out-of-vocabulary objects.

GoDeep uses a vision-language model purely as a translator, producing structured entity-level image descriptions that are grounded, projected, and aggregated in a general-purpose language-only embedding space, with no 3D training corpus or dedicated 3D encoder required. On ScanNet++ the pipeline is competitive with strong annotation-free baselines, and on a cultural-heritage benchmark a systematic vocabulary correction reverses initial CLIP-based rankings. Language-space embeddings separate genuinely out-of-vocabulary objects more sharply, localize them within scenes, and keep all predictions explainable as discrete text.

arXiv cs.AI / cs.LG / cs.CLSep 8, 17:31 UTC · 7d agoAI research

Advancing price-performance for developers with GPT‑5.6 in Kiro

OpenAI's GPT-5.6 is now available in the Kiro developer platform, offering developers improved price-performance for planning, building, reviewing, and testing software.

OpenAI announced that GPT-5.6 is now available in Kiro, a developer platform for planning, building, reviewing, and testing software. The announcement emphasizes better price-performance for developer workloads rather than new model capabilities. This expands the commercial availability of OpenAI models in third-party coding tools.

OpenAI NewsAug 24, 12:00 UTC · 23d agoAI industry

Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation

Benchmark Radar provides a living searchable database of 1,283 AI benchmark records and 12,916 score observations drawn from 37 daily discovery sources.

Benchmark Radar combines daily discovery of benchmark papers, repositories, datasets, and releases from 13 direct connectors and 24 first-party feeds into a searchable catalog with model card mentions and score histories. The catalog contains 1,283 source records drawn from 4 benchmark catalogs plus 12,916 numeric observations on 790 records. The release includes a web dashboard with leaderboard, Pareto frontier of score versus usage, saturation and trend views, daily feeds, a CLI, and reproducible analysis. The paper audits the full catalog and examines benchmark saturation and limits of score comparisons.

Hugging Face daily papersSep 9, 20:00 UTC · 6d agoAI research

MindTopo: Can Foundation Models Reason in Topological Space?

MindTopo benchmark with 11,030 topological tasks shows 14 multimodal LLMs reason better than they plan and remain far below human performance.

MindTopo is a benchmark of topological intuition across five properties grounded in cognitive science and formal topology: continuity, separation, order, enclosure, and knots, evaluated at reasoning and closed-loop planning levels. It contains 11,030 instances across 13 procedurally generated task types with controllable difficulty, benchmarking 14 multimodal LLMs plus agent configurations using image and video generation, including three video generative models. Every MLLM performs better on reasoning than on planning, and the best-performing model remains far below observed human performance. On Qwen3-VL-2B-Instruct, supervised fine-tuning and reinforcement learning improve reasoning more than planning, and audited generated rollouts often fail to follow environment dynamics or preserve topology across transitions.

arXiv cs.AI / cs.LG / cs.CLSep 10, 17:54 UTC · 5d agoAI research

Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets

Hugging Face, Strands Agents, and LeRobot integrate with Storage Buckets for a unified record-train-deploy robotics data workflow.

Hugging Face announced an integrated robotics workflow combining LeRobot, Amazon's Strands Agents, and Hugging Face Storage Buckets. The setup lets developers record robot data, stream it in a data loop, train models, and deploy agents from a single place. No article body was available, so details beyond the title are limited.

Hugging Face BlogAug 13, 17:16 UTC · Aug 13, 2026AI tools & infra

Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization

SG-JEPA world model conditions latent prediction on physical parameters, halving open-loop prediction error versus DINO-WM and boosting robotic control success.

SG-JEPA extends the LeWorldModel JEPA framework by supplying the governing physics parameter to the temporal model via action-conditioning and jointly training an encoder and predictor through autoregressive latent rollout. On out-of-distribution gravitational-field tasks it reduces open-loop prediction error by up to 2x versus DINO-WM on 2D datasets and increases 3D robotic control success rate up to 2.5x using independently trained diffusion policies. A linear feature analysis attributes most of the gain to the encoder learning features that the predictor can carry forward through rollout.

arXiv cs.AI / cs.LG / cs.CLSep 9, 17:08 UTC · 6d agoAI research

CosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements

Researchers release CosmoH2G, a 6,189-episode hand-to-gripper dataset with a two-stage method for complex spatial robot manipulation.

The paper introduces a scalable acquisition pipeline using a handheld gripper to collect paired hand-gripper demonstrations, producing 6,189 episodes across 1,254 unique objects with higher spatial complexity than existing benchmarks. A two-stage framework first predicts sparse gripper keyframes (initial and terminal), then generates the full continuous action sequence conditioned on them, while learning gripper orientation and post-optimizing translation via grasping heuristics and kinematic consistency. Simulation and real-robot experiments show stable, precise hand-to-gripper transfer of complex spatial manipulations, outperforming traditional baselines.

Hugging Face daily papersSep 6, 20:00 UTC · 9d agoAI research

IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

IdeaAMBIG benchmark of 660 specification-gap instances shows LLMs localize implementation-critical research gaps poorly, with best model at 9.6% defect recovery.

IdeaAMBIG is a benchmark of 660 evidence-grounded instances evaluating whether research-method specifications provide enough information for faithful implementation: 163 real-world gaps from reproducibility reports and GitHub issues plus 497 controlled synthetic gaps. It tests codification-readiness assessment, defect localization, and clarification action generation across 13 LLMs. The best model achieves only a 9.6% Macro Defect Recovery Rate on real-world instances, though 80.6% clarification success when given the annotated defect, and an oracle study shows gold resolutions raise codification-ready rates from 14% to 98%. Defect localization emerges as the main bottleneck across all evaluated models.

Hugging Face daily papersSep 8, 20:00 UTC · 7d agoAI research

How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code

Hugging Face explains how Inference Endpoints, Jobs, and Buckets power semantic search on Papers with Code.

Hugging Face describes the infrastructure behind search on Papers with Code, built on its Inference Endpoints, Jobs, and Buckets services. The post is a product-focused engineering walkthrough with no security impact.

Hugging Face BlogAug 21, 00:00 UTC · 26d agoAI tools & infra

Embodied-BenchForge: A Closed-Loop Agentic Workflow for Embodied Benchmark Construction

Embodied-BenchForge automates embodied benchmark construction via closed-loop synthesis with verification and repair, yielding seven benchmarks for MLLM evaluation.

Embodied-BenchForge is an agentic framework that transforms user-specified evaluation intents into complete embodied benchmark artifacts via Closed-Loop Benchmark Synthesis. Skill-Orchestrated Artifact Synthesis composes typed reusable skills while an artifact dependency graph records intermediate outputs; Requirement-Guided Verification and Repair triggers local re-execution or upstream rollback on failures. It constructs six Offline EQA benchmarks plus one interactive benchmark with 220 executable tasks, distinguishing MLLM and embodied agent capabilities in observation-based understanding and closed-loop execution.

arXiv cs.AI / cs.LG / cs.CLSep 11, 17:16 UTC · 4d agoAI research