GPT-5.4

An OpenAI model has disproved a central conjecture in discrete geometry

People are generating over 1.5 billion images a week in ChatGPT. Researcher @kenjihata joins Product lead @adele__li and host @AndrewMayne to explore the new use cases and trends emerging since the la

People are generating over 1.5 billion images a week in ChatGPT. Researcher @kenjihata joins Product lead @adele__li and host @AndrewMayne to explore the new use cases and trends emerging since the launch of Images 2.0. https://t.co/INhLS7TDri

Introducing OpenAI for Singapore

Introducing OpenAI Guaranteed Capacity: a new offering that enables customers to guarantee long-term access to OpenAI compute. We’ve made long-term investments in infrastructure, partnerships, and cap

Introducing OpenAI Guaranteed Capacity: a new offering that enables customers to guarantee long-term access to OpenAI compute. We’ve made long-term investments in infrastructure, partnerships, and capacity planning to help customers scale reliably. Now, Guaranteed Capacity

OpenAI and Malta partner to bring ChatGPT Plus to all citizens

A new personal finance experience in ChatGPT

Earlier this month, an Erdős problem that had been open for 60 years was solved with help from GPT-5.4 Pro. What happens now that AI is getting good at math? OpenAI researchers @SebastienBubeck and @E

Earlier this month, an Erdős problem that had been open for 60 years was solved with help from GPT-5.4 Pro. What happens now that AI is getting good at math? OpenAI researchers @SebastienBubeck and @ErnestRyu join host @AndrewMayne to explain what changed and what it could mean https://t.co/wqYLv1Ju2T

We’re expanding Trusted Access for Cyber with additional tiers for authenticated cybersecurity defenders. Customers in the highest tiers can request access to GPT-5.4-Cyber, a version of GPT-5.4 fine-

We’re expanding Trusted Access for Cyber with additional tiers for authenticated cybersecurity defenders. Customers in the highest tiers can request access to GPT-5.4-Cyber, a version of GPT-5.4 fine-tuned for cybersecurity use cases, enabling more advanced defensive workflows.

We're publishing a new evaluation suite and research paper on Chain-of-Thought (CoT) Controllability. We find that GPT-5.4 Thinking shows low ability to obscure its reasoning—suggesting CoT monitoring

We're publishing a new evaluation suite and research paper on Chain-of-Thought (CoT) Controllability. We find that GPT-5.4 Thinking shows low ability to obscure its reasoning—suggesting CoT monitoring remains a useful safety tool. https://t.co/isZkNkPXZm

GPT-5.4 Thinking and GPT-5.4 Pro are rolling out now in ChatGPT. GPT-5.4 is also now available in the API and Codex. GPT-5.4 brings our advances in reasoning, coding, and agentic workflows into one fr

GPT-5.4 Thinking and GPT-5.4 Pro are rolling out now in ChatGPT. GPT-5.4 is also now available in the API and Codex. GPT-5.4 brings our advances in reasoning, coding, and agentic workflows into one frontier model. https://t.co/1hy6xXLAmJ

AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents

GPU kernel optimization is increasingly critical for efficient deep learning systems, but writing high-performance kernels still requires substantial low-level expertise. Recent AI coding agents can iteratively read code, invoke compilers and profilers, and refine implementations, yet existing kernel benchmarks evaluate single LLM calls rather than full agent workflows, and none include both kernel-to-kernel optimization and unseen-configuration generalization testing. We present AgentKernelArena, an open-source benchmark for measuring AI coding agents on GPU kernel optimization. The benchmark contains 196 tasks spanning HIP-to-HIP optimization, Triton-to-Triton optimization, and PyTorch-to-HIP translation, and evaluates complete agent workflows in isolated workspaces using gated compilation, correctness, and performance checks, centralized scoring and an unseen-configuration generalization protocol that tests whether optimizations transfer to input configurations the agent never observed. Across production agents including Cursor Agent, Claude Code, and Codex Agent, we find near-perfect compilation and high correctness rates on most task categories, with the strongest configurations achieving mean speedups of up to 6.89x on PyTorch-to-HIP, 6.69x on HIP-to-HIP, and 2.13x on Triton-to-Triton tasks. Our unseen-configuration evaluation shows that HIP-to-HIP and Triton-to-Triton optimizations largely transfer to unseen input shapes, while PyTorch-to-HIP exhibits substantial correctness drops, indicating that agents generating kernels from scratch frequently hardcode shape-specific assumptions. AgentKernelArena is designed as a modular, extensible framework for rigorous evaluation of agentic GPU kernel optimization across agents, tasks, and hardware targets.

Useful Memories Become Faulty When Continuously Updated by LLMs

Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolidated abstractions distilled across many episodes into reusable, schema-like lessons. Recent agentic-memory systems pursue the consolidated form: an LLM rewrites past trajectories into a textual memory bank that it continuously updates with new interactions, promising self-improving agents without parameter updates. Yet we find that such consolidated memories produced by today's LLMs are often faulty even when derived from useful experiences. As consolidation proceeds, memory utility first rises, then degrades, and can fall below the no-memory baseline. More surprisingly, even when consolidating from ground-truth solutions, GPT-5.4 fails on 54% of a set of ARC-AGI problems it had previously solved without memory. We trace the regression to the consolidation step rather than the underlying experience: the same trajectories yield qualitatively different memories under different update schedules, and an episodic-only control that simply retains those trajectories remains competitive with the consolidators we test. In a controlled ARC-AGI Stream environment that exposes Retain, Delete, and Consolidate actions, agents preserve raw episodes by default and double the accuracy of their forced-consolidation counterparts; disabling consolidation entirely (episodic management only) matches this auto regime. Practically, robust agent memory should treat raw episodes as first-class evidence and gate consolidation explicitly rather than firing it after every interaction. Looking forward, reliable agentic memory will require LLMs that can consolidate without overwriting the evidence they depend on.

Covering Human Action Space for Computer Use: Data Synthesis and Benchmark

Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models suggests a long-tail pattern in GUI operations, where a relatively small fraction of complex and diverse interactions accounts for a disproportionate share of task failures. We hypothesize that this issue largely stems from the scarcity of data for complex interactions. To address this problem, we propose a new benchmark CUActSpot for evaluating models' capabilities on complex interactions across five modalities: GUI, text, table, canvas, and natural image, as well as a variety of actions (click, drag, draw, etc.), covering a broader range of interaction types than prior click-centric benchmarks that focus mainly on GUI widgets. We also design a renderer-based data-synthesis pipeline: scenes are automatically generated for each modality, screenshots and element coordinates are recorded, and an LLM produces matching instructions and action traces. After training on this corpus, our Phi-Ground-Any-4B outperforms open-source models with fewer than 32B parameters. We will release our benchmark, data, code, and models at https://github.com/microsoft/Phi-Ground.git

IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs

In industrial procurement, an LLM answer is useful only if it survives a standards check: recommended material must match operating condition, every parameter must respect a regulated threshold, and no procedure may contradict a safety clause. Partial correctness can mask safety-critical contradictions that aggregate LLM benchmarks rarely capture. We introduce IndustryBench, a 2,049-item benchmark for industrial procurement QA in Chinese, grounded in Chinese national standards (GB/T) and structured industrial product records, organized by seven capability dimensions, ten industry categories, and panel-derived difficulty tiers, with item-aligned English, Russian, and Vietnamese renderings. Our construction pipeline rejects 70.3% of LLM-generated candidates at a search-based external-verification stage, calibrating how unreliable industrial QA remains after LLM-only filtering.Our evaluation decouples raw correctness, scored by a Qwen3-Max judge validated at κ_w = 0.798 against a domain expert, from a separate safety-violation (SV) check against source texts. Across 17 models in Chinese and an 8-model intersection over four languages, we find: (i) the best system reaches only 2.083 on the 0--3 rubric, leaving substantial headroom; (ii) Standards & Terminology is the most persistent capability weakness and survives item-aligned translation; (iii) extended reasoning lowers safety-adjusted scores for 12 of 13 models, primarily by introducing unsupported safety-critical details into longer final answers; and (iv) safety-violation rates reshuffle the leaderboard -- GPT-5.4 climbs from rank 6 to rank 3 after SV adjustment, while Kimi-k2.5-1T-A32B drops seven positions.Industrial LLM evaluation therefore requires source-grounded, safety-aware diagnosis rather than aggregate accuracy. We release IndustryBench with all prompts, scoring scripts, and dataset documentation.

Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows

Frontier coding agents are increasingly used in workflows where users supervise progress primarily through repeated improvement of a public score, namely the reported score on a public evaluation file with labels in the workspace, rather than through direct inspection of the agent's intermediate outputs. We study whether multi-round user pressure to improve that score induces public score exploitation: behavior that raises the public score through shortcuts without improving hidden private evaluation. We begin with a preliminary single-script tabular classification task, where GPT-5.4 and Claude Opus 4.6 both exploit label information within 10 rounds of user-agent interaction. We then build AgentPressureBench, a 34-task machine-learning repository benchmark spanning three input modalities, and collect 1326 multi-round trajectories from 13 coding agents. On our benchmark, we observe 403 exploitative runs, spanning across all tasks. We also find that stronger models have higher exploitation rates, supported by a significant Spearman rank correlation of 0.77. Our ablation experiments show that higher user pressure leads to earlier exploitation, reducing the average first exploit round by 15.6 rounds (i.e., 19.67 to 4.08). As a mitigation, adding explicit anti-exploit wordings in prompt mostly eliminates exploitation (100% to 8.3%). We hope that our work can bring attention to more careful use of coding agents workflow, and developing more robust coding agents under user pressure. Our project page is at https://ucsc-vlaa.github.io/AgentPressureBench .

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline trajectories across three frontier models (Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.4). Each entry preserves the original task definition alongside full attack trajectories that show how the verifier was bypassed. It also includes cases where the task was not solved as intended. The tasks span system administration, machine learning, software engineering, and security challenges; the exploits range from simple output spoofing to stack-frame introspection, standard-library patching, and rootkit-style binary hijacking. Crucially, these exploits are specific to each task, rather than the evaluation harness, making them harder to patch. We also present a monitorability study in which hack trajectories are sanitized or stripped of reasoning traces and then scored by an LLM judge, showing that detection degrades meaningfully when chain-of-thought is removed (AUC drops from 0.97 to 0.92). The data set is publicly available at https://github.com/few-sh/terminal-wrench.

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of automation and powerful personalization, they also expose a substantial attack surface that existing sandboxed evaluations fail to capture. To address this gap, we present the first real-world safety evaluation of OpenClaw and introduce the CIK taxonomy, which unifies an agent's persistent state into three dimensions, i.e., Capability, Identity, and Knowledge, for safety analysis. Our evaluations cover 12 attack scenarios on a live OpenClaw instance across four backbone models (Claude Sonnet 4.5, Opus 4.6, Gemini 3.1 Pro, and GPT-5.4). The results show that poisoning any single CIK dimension increases the average attack success rate from 24.6% to 64-74%, with even the most robust model exhibiting more than a threefold increase over its baseline vulnerability. We further assess three CIK-aligned defense strategies alongside a file-protection mechanism; however, the strongest defense still yields a 63.8% success rate under Capability-targeted attacks, while file protection blocks 97% of malicious injections but also prevents legitimate updates. Taken together, these findings show that the vulnerabilities are inherent to the agent architecture, necessitating more systematic safeguards to secure personal AI agents. Our project page is https://ucsc-vlaa.github.io/CIK-Bench.

MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies

Currently, evaluating vision-language models (VLMs) in medical imaging tasks oversimplifies clinical reality by relying on pre-selected 2D images that demand significant manual labor to curate. This setup misses the core challenge of realworld diagnostics: a true clinical agent must actively navigate full 3D volumes across multiple sequences or modalities to gather evidence and ultimately support a final decision. To address this, we propose MEDOPENCLAW, an auditable runtime designed to let VLMs operate dynamically within standard medical tools or viewers (e.g., 3D Slicer). On top of this runtime, we introduce MEDFLOWBENCH, a full-study medical imaging benchmark covering multi-sequence brain MRI and lung CT/PET. It systematically evaluates medical agentic capabilities across viewer-only, tool-use, and open-method tracks. Initial results reveal a critical insight: while state-of-the-art LLMs/VLMs (e.g., Gemini 3.1 Pro and GPT-5.4) can successfully navigate the viewer to solve basic study-level tasks, their performance paradoxically degrades when given access to professional support tools due to a lack of precise spatial grounding. By bridging the gap between static-image perception and interactive clinical workflows, MEDOPENCLAW and MEDFLOWBENCH establish a reproducible foundation for developing auditable, full-study medical imaging agents.

Guideline-grounded retrieval-augmented generation for ophthalmic clinical decision support

In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat each guideline page as an independent evidence unit and directly retrieve page images, preserving tables, flowcharts, and layout information. We further design a controllable retrieval framework with routing and filtering, which selectively introduces external evidence and reduces noise. The system integrates query decomposition, query rewriting, retrieval, reranking, and multimodal reasoning, and provides traceable outputs with guideline page references. We evaluate our method on HealthBench using a doctor-based scoring protocol. On the hard subset, our approach improves the overall score from 0.2969 to 0.3861 (+0.0892, +30.0%) compared to GPT-5.2, and achieves higher accuracy, improving from 0.5956 to 0.6576 (+0.0620, +10.4%). Compared to GPT-5.4, our method achieves a larger accuracy gain of +0.1289 (+24.4%). These results show that our method is more effective on challenging cases that require precise, evidence-based reasoning. Ablation studies further show that reranking, routing, and retrieval design are critical for stable performance, especially under difficult settings. Overall, we show how combining visionbased retrieval with controllable reasoning can improve evidence grounding and robustness in clinical AI applications,while pointing out that further work is needed to be more complete.

Introducing GPT‑5 for developers

Introducing GPT‑5 for developers | OpenAI Skip to main content Research Products Business Developers Company Foundation (opens in a new window) Log in Try ChatGPT (opens in a new window) Research Products Business Developers Company Foundation (opens in a new window) Try ChatGPT (opens in a new window) Login OpenAI Table of contents Introduction New features Safety Availability & pricing Detailed benchmarks August 7, 2025 Product Introducing GPT‑5 for developers The best

GPT5.4 - GAIA

GAIA score 68.1 from SB-Agent