Search: “tool-calling”

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.CL·Sep 4, 17:44 UTC · 12d agoAI research1

Command integrity breaks in the LLM routing layer

Help Net Security·Apr 16, 00:00 UTC · Apr 16, 2026AI tools & infra

[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)

Latent Space AI news roundup: Steve Yegge shuts down Gas Town, Databricks reports 60% higher coding spend on GPT-6 Astra, OpenAI launches misalignment disclosure framework.

Latent Space's AI News digest for September 15-16, 2026 leads with Steve Yegge shutting down his Gas Town orchestrator despite spending thousands monthly on coding-agent subscriptions. Databricks rolled out GPT-6 Astra to roughly 3,500 engineers, reporting superior long-horizon performance over Opus 5 and Sol 5.6 but a ~60% increase in coding spend. OpenAI published a formal framework for disclosing model misalignment incidents with six case reports, while Microsoft and Google Research released safety papers on 'capability laundering' and the Fuse motive-inference benchmark. Xiaomi shared live RL training telemetry for MiMo-V2.6, estimated at $493k/day for the 1T-class Pro run.

Latent Space·07:28 UTC · 1h agoAI industry 12 sources

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 papers·Sep 8, 20:00 UTC · 8d agoAI research1

Gemini 3.8 Live and 3.8 Live Extended Thinking

Google launches Gemini 3.8 Live and 3.8 Live Extended Thinking speech models, topping speech-to-speech benchmarks with parallel reasoning for voice agents.

Google announced Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, its most advanced live dialogue models for near real-time voice agents. Extended Thinking ranks #1 on Artificial Analysis' Speech-to-Speech Quality Index (82.6), scores 68.6% on τ-Voice, 35.1% on Sierra's τ-Voice-banking, and 97.7% on Big Bench Audio. The models support 97 languages with mid-conversation switching, real-time visual grounding, background tool execution, and SynthID audio watermarking. Rollout covers the Gemini API, AI Studio, Enterprise private previews, Search Live, and Workspace.

Hacker News · AI·updated Sep 15, 20:53 UTC · 1d ago·first Sep 15, 17:38 UTC · 1d agoModel release 3 sourcesHN 44↑ · 12 comments

Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking

Google DeepMind launched Gemini 3.8 Live and 3.8 Live Extended Thinking speech models, topping Artificial Analysis' Speech-to-Speech Quality Index at 82.6.

Google DeepMind released Gemini 3.8 Live, built for cost-efficient near-real-time dialogue with visual grounding, and 3.8 Live Extended Thinking for high-complexity multi-step reasoning. Extended Thinking ranks #1 on Artificial Analysis' Speech to Speech Quality Index (82.6), scores 68.6% on τ-Voice, 35.1% on Sierra's τ-Voice-banking, and 97.7% on Big Bench Audio. The models detect and switch among 97 languages mid-conversation, execute background tool and API calls, and roll out in the Gemini API, AI Studio, Gemini Enterprise private preview, and Search Live. All generated audio is watermarked with SynthID.

Google DeepMind·updated Sep 15, 20:53 UTC · 1d ago·first Sep 15, 17:05 UTC · 1d agoModel release 3 sources10

Agent-net Open Sources Webagent: A Go Harness That Turns Any Website into a Guarded AI Agent

Agent-net open-sourced Webagent, a Go harness turning websites into AI agents with code-enforced guardrails wrapping every tool call.

Agent-net released Webagent under Apache 2.0, a Go framework where a business fills in a declarative JSON spec, picks one provider for each of nine pluggable slots (retrieval, memory, guardrail, channel, secrets, presenter, model, action, observability), and runs webagent serve. Every tool the agent holds is wrapped by action.Guard so the chosen guardrail executes before any action runs and the model cannot bypass it. Live capabilities include OpenRouter/gateway LLM brains, MCP tools over Streamable HTTP, and Slack, WhatsApp, and HTTP channels; browser actions, OAuth-gated MCP, OTel export, and AgentNet identity/billing are not yet built. The project is v0 with a deferred-hardening list and cites arXiv 2511.19477 on an 85% versus 50% task-success gap attributed to architecture over model capability.

MarkTechPost·Sep 15, 04:03 UTC · 2d agoAI tools & infra1

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 · AI·Sep 14, 13:59 UTC · 2d agoAI industryHN 41↑ · 13 comments1

The AI Supply Chain Has a Security Problem, and Much of It Is Sitting on the Open Internet

Researchers counted 36,769 publicly reachable self-hosted AI endpoints, only about 2% behind HTTP authentication, exposing Ollama, vLLM, and Flowise to abuse.

A Mysterium VPN study found 36,769 self-hosted AI endpoints reachable through internet scanning, with only 2.02% returning an HTTP authentication challenge. Open WebUI accounted for 18,529 reachable instances, Ollama for 6,935 fingerprinted hosts, and 5,223 agent-builder and workflow platforms were exposed, often holding API keys, database credentials, and other secrets. The report highlights LLMjacking risk from exposed Ollama APIs, a critical Flowise bug (CVE-2026-40933), leaked n8n tokens, and prior SentinelOne/Censys research finding roughly 175,000 exposed Ollama hosts in 130 countries.

Security Affairs·Sep 11, 17:27 UTC · 5d agoAI safety & securityCVE-2026-409331

Agnes-AI/Agnes-3.0-Flash — new model trending #30 on Hugging Face

Agnes AI releases open-weight Agnes-3.0-Flash Preview, a 33B multimodal model with 262k-token context under Apache 2.0.

Agnes AI released Agnes-3.0-Flash Preview, an open-weights multimodal checkpoint with 33B parameters and a 262,144-token context window under Apache 2.0. The model supports text, image, and video understanding, tool calling, and adjustable reasoning effort. The repo clarifies this preview checkpoint is distinct from the production/API Agnes 3.0 Flash model, which uses a different configuration with a 1M-token context window. Reported reference results include IFBench 74.20 and SciCode 38.08 against peers such as Qwen3.6-35B-A3B, Kimi K2.5, and MiniMax M3.

Hugging Face trending models·Sep 11, 15:50 UTC · 5d agoModel release

ukisai/Swift-Qwen3.8-27B-GGUF — new model trending #30 on Hugging Face

UkisAI released Swift-Qwen3.8-27B GGUF, a Qwen3.8-27B derivative cutting thinking tokens by 58.3% with under 1% performance loss and roughly 1.95x speedup.

UkisAI released Swift-Qwen3.8-27B as GGUF on Hugging Face, a reasoning-efficient derivative of Qwen3.8-27B using a Swift adapter that reduces median thinking tokens by up to 58.3% while keeping performance losses under 1% and delivering a 1.95x speed-up on several tasks. Reported benchmarks include GPQA-Diamond 88.28%, MMLU-Pro 84.95%, C-Eval 90.62%, AIME 2026 94.00% and Terminal-Bench 2.1 65.84%. The model is trending at #30 on Hugging Face, with BF16 weights and enterprise licensing also available.

Hugging Face trending models·Sep 11, 14:58 UTC · 5d agoModel release

Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks

Context segmentation framework boosts memory-constrained gemma-4 agents on picoCTF, solving 18.52% of tasks standard execution fails, highlighting local SLM offensive risk.

The paper introduces context segmentation, a two-level agentic framework that divides long-horizon CTF exploitation tasks into contextually isolated sub-problems to counter context bloat and cognitive degradation from accumulated tool-call outputs. It evaluates memory-constrained gemma-4 models on the picoCTF dataset; the E4B model achieves competitive rewards with superior token efficiency compared to brute-force retries. It solves 18.52% of tasks that standard agentic execution fails to complete. The work frames locally deployed open-weight SLMs as an escalating risk since they bypass proprietary API guardrails; code is released on GitHub.

arXiv cs.CR·Sep 11, 13:34 UTC · 5d agoAI safety & security1

OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time

OpenAI's GPT-Live-1 API enables full-duplex speech apps, outperforming GPT-Realtime-2.1 with 0.8s turn-taking latency at $0.05 per minute.

OpenAI released GPT-Live-1 as a developer API for full-duplex speech, allowing applications to listen and talk simultaneously; it already powers ChatGPT voice. Benchmarks show 80.1% on full-duplex interactivity versus 45.4% for GPT-Realtime-2.1, turn-taking latency of 0.8 seconds versus 1.4 seconds, tool-calling accuracy of 87% versus 60%, and a 32% pass rate on a banking voice-support benchmark versus 12.4%. The model costs $0.05 per minute, ships twelve new voices, provides ASR transcripts and response text, and is already in production at Yelp for phone-based reservations.

The Decoder·Sep 10, 17:47 UTC · 6d agoModel release1

Build more natural voice experiences with GPT‑Live‑1 in the API

OpenAI releases GPT-Live-1 in the API, a full-duplex voice model that handles interruptions natively and delegates reasoning to backend models.

OpenAI launched GPT-Live-1 in the API, a single-model full-duplex voice system that listens and speaks simultaneously, replacing chained STT-LLM-TTS architectures. It improves Full Duplex Bench performance by 30 percentage points over GPT-Realtime-2.1 and ranks #1 on Tau3 when paired with GPT-6 Astra at medium reasoning effort. Early partner Speak reported nearly 80% fewer interruptions in language tutoring. The API release costs $0.05 per minute for the front-end voice layer and supports telephony, native ASR transcripts, keyword biasing, and expanded voice and language options.

OpenAI News·Sep 10, 00:00 UTC · 7d agoModel release1

Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision

ECCV 2026 challenge winner reformulates egocentric intervention timing as single-token classification, boosting macro-F1 by 0.249 over free-form generation.

The paper describes the winning submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, ranking first in the large-model division and second in the <=2B division. The method reformulates intervention timing as single-token yes/no classification, improving macro-F1 by 0.249 and G-mean by 0.30 over free-form generation. Supervision generated by a tool-calling video agent transferred better than a narration-only dataset that was four times larger and ten times cheaper, suggesting visual grounding matters more than annotation volume.

Hugging Face daily papers·Sep 9, 20:00 UTC · 7d agoAI research

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

T1, a 122B MoE terminal agent trained with reinforcement learning, reaches 64.0% on Terminal-Bench 2.1, surpassing GPT-5.4 and GLM-5.1 on long-horizon tasks.

T1 is a 122B mixture-of-experts model trained with reinforcement learning to operate a real shell in a cloud sandbox for up to 300+ tool-call turns per task, rewarded by executing each task's own verifier. The recipe combines aggressive warm starts, dense process rewards, TITO construction, and rollout routing replay, cutting the training-to-inference log-probability difference from 0.021 to 0.013 with zero token drift. Training used an out-of-distribution corpus disjoint from Terminal-Bench 2.1. Post-training raised the base model from 43.8% to 64.0% resolved on Terminal-Bench 2.1 and 27.9% on Long-Horizon Terminal Bench.

Hugging Face daily papers·Sep 9, 20:00 UTC · 7d agoAI research1

IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier

IB2 protocol scores enterprise AI systems by serving route with reliability-inclusive scoring; serving-arm choice moved one score from 77.38 to 82.54.

The protocol has three parts: a gold-blind capability-binding preflight verifying a route can execute the evaluation contract, a reliability-inclusive first-pass scoring rule, and structurally score-blind adjudication. Its reference instantiation uses 128 locked tasks and 987 assertions over document, spreadsheet, chart, tool, and database work, released as procedure and schemas rather than an exposed corpus. Across eleven systems, two complete runs on identical weights later failed distinct binding-gate predicates, four of seven suites saturate within a six-system band driven by governed database work and multi-tab joins, and excluding failed responses from denominators changes the point ordering. Serving-arm choice shifted one declared revision and precision from 77.38 to 82.54, though arms differed in access mode, harness generation, and the tool-call parser.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 17:31 UTC · 7d agoAI research1

When the prompt becomes the payload: A practical pen-testing guide for GenAI, LLM and RAG applications

CSO Online publishes a practical penetration-testing guide for GenAI, LLM, and RAG applications, covering prompt injection, retrieval poisoning, and tenant isolation testing.

The guide frames LLM applications as attack graphs spanning prompts, retrieval layers, vector stores, tools, identities, and downstream APIs, arguing that conventional web testing misses instruction-vs-data channel risks. It builds on OWASP prompt injection guidance (direct vs. indirect injection) and NIST's 2025 adversarial machine-learning taxonomy, noting that RAG and fine-tuning do not remove injection risk. Recommended practices include documenting trust transitions across components, using canaries and synthetic records to avoid test side effects, running multi-turn and obfuscated injection campaigns, and verifying chains from poisoned documents to observable state changes. It also details testing RAG pipelines via controlled document poisoning across metadata, OCR layers, and code comments, plus cross-tenant isolation checks on retrieved document IDs.

CSO Online·Sep 9, 10:00 UTC · 7d agoAI safety & security1

OpenBMB Releases MiniCPM5-2B: A 2.52B Dense Model Averaging 53.9 Across 34 Benchmarks and Built to Run On Device

OpenBMB released MiniCPM5-2B, a 2.52B-parameter Apache 2.0 on-device model averaging 53.9 across 34 benchmarks, ahead of Qwen3.5-4B.

OpenBMB released MiniCPM5-2B, a 2,516,756,480-parameter dense LlamaForCausalLM model with grouped-query attention and a 131,072-token context, under Apache 2.0, runnable via vLLM, SGLang, llama.cpp, and Ollama. It averages 53.9 across 34 benchmarks versus 51.1 for Qwen3.5-4B, with strong tool-use (97.1 on tau2-Bench Telecom) and code results (69.1 LiveCodeBench v6, 46.4 SWE-bench Verified). Training combined 400B tokens of deep-thinking SFT, critic-based JustRL II RL teachers, and on-policy distillation merging 16 RL experts; datasets and intermediate checkpoints were published alongside the weights.

MarkTechPost·Sep 7, 19:18 UTC · 9d agoModel release

Jackrong/Qwopus3.8-27B-Flash-GGUF — new model trending #26 on Hugging Face

Community fine-tune Qwopus3.8-27B-Flash, built on Qwen3.8-27B, cuts agent reasoning latency with 12.8% faster decoding and 80.7% MTP acceptance.

Jackrong released Qwopus3.8-27B-Flash, a fine-tune of Qwen3.8-27B optimized for long-running agent workloads, reporting 12.8% faster decoding and 80.7% multi-token-prediction acceptance. Training used roughly 1.5 million teacher-scored SFT examples filtered to the top 10%, followed by reinforcement training with NVIDIA NeMo-RL and GSPO. The author notes an explicit trade-off: MMLU-Pro mixed-set scores are lower than the base model, and a known bug can produce incorrect Python indentation. Author-provided benchmarks have not been independently verified.

Hugging Face trending models·Sep 4, 12:43 UTC · 12d agoModel release2