Search headlines, summaries and articles to connect the dots.
Agentic assistants built on frontier models run a multi-step tool loop, and paying frontier prices on every step is hard to sustain at production scale. This post shows how to use sequence-level knowledge distillation (SeqKD) to transfer a frontier teacher's agentic behavior into a small, lower-cost student on Amazon SageMaker AI.
What do LLMs think about vision models?
Introducing LifeVal, a benchmark measuring how well AI helps people complete everyday tasks, from finding childcare to managing finances and government paperwork.
Evaluating Microsoft Copilot at enterprise scale requires test data that captures the full complexity of real organizations, yet real enterprise data contains sensitive information that cannot be used for evaluation under any circumstances. The post From synthetic enterprise data evaluations to real Microsoft Copilot AI confidence appeared first on Microsoft Research.
arXiv:2610.37905v1 Announce Type: new Abstract: Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents requires discovering unstated deficiencies across related documents, acquiring missing company facts, and verifying that requested revisions satisfy evidence-backed requirements. Existing financial question-answering evaluations provide limited evidence of these interactive capabilities. We introduce \textbf{FilingLoop}, an interactive benchmark and a self-evolving agent framework for corporate disclosure review and revision. Grounded in historical U.S.\ Securities and Exchange Commission correspondence, FilingLoop reconstructs 380 predominantly IPO review tasks from 96 compan
arXiv:2610.37679v1 Announce Type: new Abstract: Tool-using language agents are vulnerable to indirect prompt injection, and a growing literature probes model internals to catch unsafe actions before they execute, with sharply conflicting results. We argue much of the conflict is an evaluation artifact, and propose a double-stratification protocol: separate injection exposure from behavioral commitment, in both the evaluation and the training population. On the primary Qwen AgentDojo grid, monitors trained on the naive mixed unsafe-versus-rest contrast mostly learn exposure: they flag exposed trajectories whether or not the agent complies, and barely predict which cases turn unsafe. Retrained on exposed cases only, the same probe families predict the model's own unsafe tool call up to two s
arXiv:2610.37851v1 Announce Type: new Abstract: Existing scientific-agent benchmarks rarely evaluate whether agents can reconstruct the exact molecular structures and generation workflows specified by sequencing protocols, a capability critical for analyzing customized sequencing assays. We introduce LibStructBench, a document-grounded benchmark for reconstructing sequencing-library structures and molecular workflows. Our experiments show that frontier agents often produce approximately correct reconstructions but remain unreliable at exact reconstruction, particularly in molecular-state representation and workflow connectivity. Switching the underlying language model produced larger average performance differences than switching agent harnesses, with a statistically significant difference
arXiv:2610.37676v1 Announce Type: new Abstract: Automated interpretability scores an explanation of a sparse-autoencoder (SAE) feature by asking a model to predict, token by token, where the feature fires on evaluation examples or to judge whether marked tokens fit it. We find that the evaluation data standard pipelines build can be scored without reading the explanation. On Neuronpedia's stored fuzzing runs for 500 random GPT-2 small features, 91.3% of activating examples are cropped with the peak on the centre token, and a rule that says "yes" when the centre token is marked reaches balanced accuracy 0.979, against 0.838 for the stored LLM scorers (recomputed from the stored per-item verdicts, on marks rebuilt from the pipeline's code); a rule reading only the mark count reaches 0.969. T
arXiv:2610.37859v1 Announce Type: new Abstract: Language-model agents differ fundamentally from prior intelligent systems in their ability to learn from natural language in context. This capability enables agents to iteratively refine their answers in response to feedback, a prevalent mode of operation in modern agentic workflows. However, the community primarily ranks models by metrics such as Pass@1 or Pass@K, which cannot capture how they utilize feedback on prior attempts. We introduce Seq@K, a natural evaluation protocol that measures whether a model can solve a problem within K sequential attempts, provided feedback after each previous failure. Unlike multi-turn agentic benchmarks that examine long-horizon planning, Seq@K isolates and formalizes the core capability of refinement from
The weights of Mistral Large 4 (Le Chonk) are now open. A 1T parameter multimodal model, and best open-weight model for coding, trained in Europe.
Infini-AI-Lab released Hermit, an Apache-2.0 harness adapter framework that trains an external layer of instructions, skills, memory and tools from task feedback, leaving the agent’s model and harness unchanged. The post Infini-AI-Lab Releases Hermit, an Open-Source Harness Adapter Framework for AI Agents appeared first on MarkTechPost.
Google’s new frontier model leads independent evals, with access initially limited to trusted defenders.
A sort of review of the benchmarking industry and what's missing.
Google DeepMind released Genie 4 as a research preview. The real-time world model adds native audio, live dialogue and text steering, with Gemini 3.8 Flash planning events inside the simulation loop. The post Meet Google DeepMind’s Genie 4: Real-Time World Model With Native Audio appeared first on MarkTechPost.
arXiv:2610.36523v1 Announce Type: new Abstract: As agents collaborate on longer tasks, responsibility may pass between models before the work is complete. The receiving model must build on prior decisions, observations, and actions while addressing the remaining requirements. Evaluating this transition requires connecting the information preserved at handoff to how the receiver continues the work, a relationship that task-success and memory-retention scores alone do not capture. We introduce the Handoff State Continuity Benchmark (HSC-Bench), comprising 1,039 tasks that evaluate two complementary aspects of task takeover: recovering relevant repository evidence and continuing from established conversational, tool, and file-work state. Comparisons across six receiving models show that struc
arXiv:2610.36178v1 Announce Type: new Abstract: We measure, without sampling error, the probability a language model assigns to each integer from 1 to N when asked for a random number. For a fixed prompt the model defines one probability vector, which we compute by summing over each integer's scored spellings rather than estimate by sampling, removing the noise that limits earlier studies [1, 4]. We evaluate 18 open-weight model lines at five ranges up to N = 100, under 29 decoding configurations, on two inference stacks; 15 of them have matched base and instruction-tuned checkpoints that both give usable answers. Instruction tuning makes the distribution less uniform in all 15 pairs. It installs one heuristic, round-number avoidance, and sharpens another, endpoint avoidance. Base checkpoi
arXiv:2610.36184v1 Announce Type: new Abstract: Bengali, spoken by over 230 million people, remains severely under-resourced in spoken language research. Existing open Bengali ASR corpora are confined to short, read or crowd-sourced speech and lack speaker diarization and long-form audio. We present Lipi-Ghor, a large-scale weakly-supervised Bengali speech corpus comprising 885 hours of audio sourced from 998 YouTube videos across 596 unique channels, spanning 17 diverse domains including audiobooks, drama, religious sermons, news, and regional dialects. Each recording is annotated in SSTT format (Speaker, Speech, Transcription, Timestamp), which combines automated diarization with Bengali YouTube caption tracks. To our knowledge, Lipi-Ghor is the first Bengali speech corpus to pair large-
arXiv:2610.36524v1 Announce Type: new Abstract: Can controlled symbolic inputs reveal attention heads that influence a language model's decisions from natural language evidence? We introduce controlled evidence aggregation (CEA), which varies the counts and order of two symbols in otherwise fixed prompts and measures changes in a frozen Transformer's preference between two answer tokens. The preference is measured by their logit difference; the prompts prescribe no correct answer. Balanced utility causal selection (BUC) identifies compact head sets by jointly evaluating how much ablating their outputs removes the count effect and how closely patching mean outputs between count conditions recovers the effect in both directions. We derive conditional bounds linking head attribution to interv
arXiv:2610.36511v1 Announce Type: new Abstract: A major challenge facing AI scientific discovery pipelines is how to determine when a generated idea is meaningfully novel. Ideally, novelty checks in these pipelines must be able to reject non-novel ideas while not rejecting too many novel ideas, and they should also be able to distinguish which parts of a proposal are non-novel, as opposed to opaquely discarding entire proposals. We design an analytical framework for evaluation of novelty checks with temporal ground truth at both the proposal- and claim-level, using four datasets of 1,060 proposals built from published papers, reviewer disputes, and generated ideas matching ones the field went on to publish. Auditing existing novelty checks with this framework, we find that checks with high
NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
