Researchers have proposed LOTUS, a framework for hallucination detection that uses multilinear low-rank decomposition to extract signals from hidden LLM layers. By analyzing peak activations and cross-layer patterns, the method identifies incorrect responses more effectively than existing pooling-based techniques.
Researchers have developed TraceQuery, a sparse decoding framework that reduces the computational cost of diffusion large language models (dLLMs). By analyzing denoising trajectories, the method selectively recomputes only necessary token representations rather than performing redundant operations, maintaining high accuracy with fewer computations.
Researchers introduced Recursive Semantic Divergence (RSD), an unsupervised metric that measures and penalizes inconsistency in LLM agent trajectories. By applying RSD as a reward signal during fine-tuning, models exhibit significantly more stable behavior and higher success rates across tool-use benchmarks.
IBM Research released vLLM-Hook MIA, a plugin for the open-source vLLM inference engine that lets developers observe and intervene in a model's internal states at runtime — for example to decline malicious prompts, flag hallucinated facts, or adjust tone — without disabling vLLM's fast graph-replay execution mode. According to IBM's technical report, MIA is up to 20x faster than the earlier vLLM-Hook and up to 14x faster than methods that insert code directly into the model. In tests, steering an 8B Llama or 1.5B Qwen model added only about 2% latency, and a 70B Llama model added about 6%.
Allen Institute for AI (Ai2) released FairStress, a benchmark that tests demographic fairness in LLMs not just by their final decisions but by how easily those decisions change under persuasive pressure. Testing open and frontier models including Olmo, Llama, Qwen, Gemma, Claude, and GPT found that models often abandon correct, well-supported decisions more readily when doing so favors a minority-coded candidate — a pattern the authors call 'anti-stereotypical over-correction.' The benchmark covers 300 scenarios across 29 domains (hiring, lending, healthcare, education, housing, criminal justice), expanded via demographic and persuasion variations into over 13 million test cases, plus a smaller 50K-item 'FairStress-Core' subset for faster evaluation.
Google introduced TorchTPU, a native PyTorch backend for Cloud TPUs (torch.device("tpu")), and co-developed a fork of Meta's TorchTitan trainer adapted for TPU training. Previously, running PyTorch training on TPUs meant rewriting code in JAX or relying on the older torch_xla path; now only minimal device-initialization changes are needed. The fork provides tested recipes for pre-training large dense models (Llama 3 70B/405B, Qwen 3 8B/32B), Mixture-of-Experts models (Qwen 3 235B), and diffusion transformers (FLUX.1 12B), plus a 'Graph Trainer' that captures an entire training step as one XLA program for better compiler optimization.
Google Research announced the final milestone of its Coral NPU open hardware standard — a 32-bit RISC-V architecture with a new Matrix Execution Unit for up to 1 TOPS at roughly 10mW — plus a v1.0 open-source IREE/MLIR compiler that takes JAX, PyTorch and TensorFlow models directly to the hardware. Synaptics is launching the first commercial silicon built on this standard, including the Astra SR200 microcontroller series (400 GOPS) and new Coralboard SR and SL developer kits, with the SL now generally available via DigiKey. Google is also partnering with VeriSilicon and GlobalFoundries to bring the open RTL into production chips.
A new study questions the common belief that whether an AI agent falls for a prompt injection is settled the moment it reads the malicious text. The researchers built a branching-rollout technique on AgentDojo benchmarks: they replayed an agent's run up to the point it encounters an injected instruction, then let the rest of the episode play out many different ways to measure how much of the final outcome was already locked in versus still open. For a Qwen3 agent running without extended reasoning, 91% of the outcome was already determined at that moment; switching on reasoning ('thinking') cut that figure to 62%, showing the agent's compliance decision often keeps forming well after it first sees the attack. Enabling reasoning also cut Qwen3's susceptibility to successful attacks, but made two other tested models more vulnerable, and benchmark scores for reasoning agents flipped on a rerun as often as 35% of the time.
AWS released a push-based NIXL connector for vLLM that changes how key-value (KV) cache data moves between prefill and decode instances in disaggregated LLM serving. Instead of the decode instance pulling KV blocks after prefill finishes, the decode instance registers its target memory in advance and the prefill instance writes the KV data directly once ready, moving coordination work off the critical path. Benchmarked on a 1-prefill/1-decode Qwen3-32B deployment using EC2 P5en instances with EFA, push mode delivered up to 3x better time-to-first-token (TTFT) and up to 30% better time-per-output-token (TPOT) than the default pull mode, especially under high request rates.
Google Research describes new work on grounding AI agents in physical lab reality, using a digital-twin framework called VERID to let agents safely plan and execute liquid-handling robot protocols. Combined with closed-loop molecular design cycles for aptamers and proteins, the agents iteratively learned from wet-lab results, improving hit rates over multiple rounds and discovering single-digit nanomolar protein binders for a cancer-related target.
Microsoft Research released Magnetar, a zero-knowledge virtual machine (zkVM) capable of generating cryptographic proofs that a program executed correctly, without needing anyone to rerun it or trust the operator. Instead of forcing developers to rewrite applications as custom cryptographic circuits, Magnetar proves standard RISC-V machine code, so programs written in Rust, Go, or C can be compiled normally and proven as-is. Benchmarks across 15 programs show it processing 7.2 to 8.7 million instructions per second on a laptop, with proofs checkable in roughly 12 milliseconds, and its cryptographic security depends only on established hash functions like SHA-256 or SHA-3 rather than elliptic curves or lattice-based schemes.
IBM Research used a coordinated multi-agent 'agent factory' to explore hardware design optimizations for a quantum error-correction decoder, comparing proprietary and open frontier models under the same 100-hypothesis search budget. The open-model configuration, run on-premises via IBM's llm-d distributed inference framework, achieved a 52x speedup over baseline for about $26 in inference cost, versus $299 for a proprietary-model configuration that reached a higher 204x speedup. The study highlights that cache-aware routing and efficient serving (98% prefix-cache hit rate, ~$0.11 per million tokens) made the open-model approach dramatically cheaper while still finding valid, compact hardware designs.
Amazon Web Services researchers published a method called 'priming' that converts pretrained Transformer models into hybrid architectures mixing attention and state space model (SSM) layers, reusing existing weights instead of retraining from scratch. The approach cuts pretraining costs by over 99% and lets a 32-billion-parameter hybrid model match its source Transformer's quality while decoding up to twice as fast. Amazon tested three SSM types and released an open-source model zoo, training code, and serving tools under Apache 2.0.
GitHub has published ReviewBench, a research-preview benchmark designed to compare AI code review agents on a common, auditable standard. The dataset draws on 219 real public pull requests across 19 languages and 187 repositories, chosen to mirror the language and size distribution found across 103.9 million GitHub pull requests. Ground truth comes from a blended pool of human reviewers, static analysis tools, and multiple frontier LLMs, cross-checked by senior engineers who agreed with the benchmark's labels 96.6% of the time. GitHub says it has already used ReviewBench internally to track its own Copilot code review (CCR) product, and that offline benchmark movement reliably predicted the direction of later production A/B tests.