Tu Vu

Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find that skill evolution complements model scaling: larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them. We also find that evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills. Finally, our ablation studies confirm that persistent knowledge accumulation in the wiki is critical for effective skill evolution. These results demonstrate the benefits of systematically accumulating and refining agent experience for developing reusable and transferable skills.

Coding agents are increasingly used as general-purpose problem solvers, but they often lack the domain expertise required for specialized tasks. Agent skills address this limitation through reusable modules that package instructions, scripts, and resources to augment agents with specialized capabilities. However, these skills are typically hand-crafted, which limits their scalability. We ask whether agents can instead acquire such skills automatically from experience. We introduce EvoSkill, a framework for automated skill acquisition. EvoSkill iteratively analyzes execution failures to identify capability gaps, proposes new skills or refinements to existing ones, and materializes them as structured skill folders. Candidate skills are selected based on held-out validation performance, while model parameters remain fixed. We evaluate EvoSkill on diverse benchmarks spanning financial-document reasoning, web search, multi-source reasoning, and coding (OfficeQA, SealQA, FRAMES, and LiveCodeBench), using models from the Claude, Gemini, Kimi, and gpt-oss families as executors. We show that EvoSkill can substantially improve agent performance across benchmarks, including gains of 15.7 points on SealQA and 11.4 points on OfficeQA. In a controlled comparison, skill evolution with EvoSkill substantially outperforms prompt evolution with GEPA. We further find evidence that evolved skills can transfer across settings: a search skill evolved on SealQA improves BrowseComp accuracy by 5.3 points without modification, while reuse across executor models improves performance in several model pairings, with outcomes depending on model and harness compatibility.

We introduce SealQA, a challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful results. SealQA comes in three flavors: (1) Seal-0 (main) and (2) Seal-Hard, both of which assess factual accuracy and reasoning capabilities, where Seal-0 targets the most challenging questions that frontier non-reasoning models (e.g., GPT-4.1) answer with near-zero accuracy; and (3) LongSeal, which extends SealQA to test long-context, multi-document reasoning in "needle-in-a-haystack" settings. Our evaluation reveals critical limitations in current models. Even frontier reasoning models face significant challenges across SealQA flavors. On Seal-0, GPT-5 with tools achieves only 43.2% accuracy at its best reasoning effort. We also find that even advanced reasoning models (e.g., DeepSeek-R1) can be vulnerable to noisy search results. Notably, increasing test-time compute does not yield reliable gains across GPT-5 and the o-series of models, with performance often plateauing or even declining early. Finally, while current models are less affected by the "lost-in-the-middle" issue, they still fail to reliably identify relevant documents in LongSeal when faced with numerous distractors. To facilitate future work, we release SealQA at https://huggingface.co/datasets/vtllms/sealqa.

We investigate whether post-trained capabilities can be transferred across model scales without retraining, and propose the Master Key Hypothesis, which states that model capabilities correspond to directions in a low-dimensional latent subspace that induce specific behaviors and are transferable across models through linear alignment. Based on the hypothesis, we introduce UNLOCK, a training-free and label-free framework that extracts a capability direction by contrasting activations between capability-present and capability-absent Source variants, aligns it with a Target model through a low-rank linear transformation, and applies it at inference time to elicit the behavior. Experiments on reasoning behaviors, including Chain-of-Thought (CoT) and mathematical reasoning, demonstrate substantial improvements across model scales without training. For example, transferring CoT reasoning from Qwen1.5-14B to Qwen1.5-7B yields an accuracy gain of 12.1% on MATH, and transferring a mathematical reasoning direction from Qwen3-4B-Base to Qwen3-14B-Base improves AGIEval Math accuracy from 61.1% to 71.3%, surpassing the 67.8% achieved by the 14B post-trained model. Our analysis shows that the success of transfer depends on the capabilities learned during pre-training, and that our intervention amplifies latent capabilities by sharpening the output distribution toward successful reasoning trajectories.

As large language models (LLMs) advance, it becomes more challenging to reliably evaluate their output due to the high costs of human evaluation. To make progress towards better LLM autoraters, we introduce FLAMe, a family of Foundational Large Autorater Models. FLAMe is trained on our large and diverse collection of 100+ quality assessment tasks comprising 5M+ human judgments, curated and standardized using publicly released human evaluations from previous research. FLAMe significantly improves generalization to a wide variety of held-out tasks, outperforming LLMs trained on proprietary data like GPT-4 and Claude-3 on many tasks. We show that FLAMe can also serve as a powerful starting point for further downstream fine-tuning, using reward modeling evaluation as a case study (FLAMe-RM). Notably, on RewardBench, our FLAMe-RM-24B model (with an accuracy of 87.8%) is the top-performing generative model trained exclusively on permissively licensed data, outperforming both GPT-4-0125 (85.9%) and GPT-4o (84.7%). Additionally, we explore a more computationally efficient approach using a novel tail-patch fine-tuning strategy to optimize our FLAMe multitask mixture for reward modeling evaluation (FLAMe-Opt-RM), offering competitive RewardBench performance while requiring approximately 25x less training datapoints. Overall, our FLAMe variants outperform all popular proprietary LLM-as-a-Judge models we consider across 8 out of 12 autorater evaluation benchmarks, encompassing 53 quality assessment tasks, including RewardBench and LLM-AggreFact. Finally, our analysis reveals that FLAMe is significantly less biased than these LLM-as-a-Judge models on the CoBBLEr autorater bias benchmark, while effectively identifying high-quality responses for code generation.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

Most large language models (LLMs) are trained once and never updated; thus, they lack the ability to dynamically adapt to our ever-changing world. In this work, we perform a detailed study of the factuality of LLM-generated text in the context of answering questions that test current world knowledge. Specifically, we introduce FreshQA, a novel dynamic QA benchmark encompassing a diverse range of question and answer types, including questions that require fast-changing world knowledge as well as questions with false premises that need to be debunked. We benchmark a diverse array of both closed and open-source LLMs under a two-mode evaluation procedure that allows us to measure both correctness and hallucination. Through human evaluations involving more than 50K judgments, we shed light on limitations of these models and demonstrate significant room for improvement: for instance, all models (regardless of model size) struggle on questions that involve fast-changing knowledge and false premises. Motivated by these results, we present FreshPrompt, a simple few-shot prompting method that substantially boosts the performance of an LLM on FreshQA by incorporating relevant and up-to-date information retrieved from a search engine into the prompt. Our experiments show that FreshPrompt outperforms both competing search engine-augmented prompting methods such as Self-Ask (Press et al., 2022) as well as commercial systems such as Perplexity.AI. Further analysis of FreshPrompt reveals that both the number of retrieved evidences and their order play a key role in influencing the correctness of LLM-generated answers. Additionally, instructing the LLM to generate concise and direct answers helps reduce hallucination compared to encouraging more verbose answers. To facilitate future work, we release FreshQA at github.com/freshllms/freshqa and commit to updating it at regular intervals.

We study the design decision of publicly available instruction tuning methods, by reproducing and breaking down the development of Flan 2022 (Chung et al., 2022). Through careful ablation studies on the Flan Collection of tasks and methods, we tease apart the effect of design decisions which enable Flan-T5 to outperform prior work by 3-17% across evaluation settings. We find task balancing and enrichment techniques are overlooked but critical to effective instruction tuning, and in particular, training with mixed prompt settings (zero-shot, few-shot, chain-of-thought) actually yields equivalent or stronger (2%) performance in all settings. In further experiments we show Flan-T5 requires less finetuning to converge higher and faster than T5 on single downstream tasks – motivating instruction-tuned models as more computationally-efficient starting checkpoints for new tasks. Finally, to accelerate research on instruction tuning, we make the Flan 2022 collection of datasets, templates, and methods publicly available.

Sparse Mixture-of-Experts (MoE) is a neural architecture design that adds learnable parameters to Large Language Models (LLMs) without increasing computational complexity (FLOPs). Instruction tuning is a technique for training LLMs to follow instructions. We advocate combining these two approaches, as we find that MoE models benefit more from instruction tuning than dense models. In particular, we conduct empirical studies across three experimental setups: (i) Direct finetuning on individual downstream tasks devoid of instruction tuning; (ii) Instruction tuning followed by in-context few-shot or zero-shot generalization on downstream tasks; and (iii) Instruction tuning supplemented by further finetuning on individual downstream tasks. In the first scenario, MoE models overall underperform dense models of identical computational capacity. This narrative, however, dramatically changes with the introduction of instruction tuning (in the second and third scenarios), used independently or in conjunction with task-specific finetuning. Our most powerful model, FLAN-MoE-32B, surpasses the performance of Flan-PaLM-62B on four benchmark tasks, while using only a third of the FLOPs. The advancements embodied by FLAN-MoE inspire a reevaluation of the design principles of large-scale, high-performance language models in the framework of task-agnostic learning.

There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a frozen pre-trained model to perform different tasks, we propose a novel prompt-based transfer learning approach called SPoT: Soft Prompt Transfer. SPoT first learns a prompt on one or more source tasks and then uses it to initialize the prompt for a target task. We show that SPoT significantly boosts the performance of Prompt Tuning across many tasks. More remarkably, across all model sizes, SPoT matches or outperforms standard Model Tuning (which fine-tunes all model parameters) on the SuperGLUE benchmark, while using up to 27,000\mbox\times fewer task-specific parameters. To understand where SPoT is most effective, we conduct a large-scale study on task transferability with 26 NLP tasks in 160 combinations, and demonstrate that many tasks can benefit each other via prompt transfer. Finally, we propose an efficient retrieval approach that interprets task prompts as task embeddings to identify similar tasks and predict the most transferable source tasks for a novel target task.

Recent advances in NLP demonstrate the effectiveness of training large-scale language models and transferring them to downstream tasks. Can fine-tuning these models on tasks other than language modeling further improve performance? In this paper, we conduct an extensive study of the transferability between 33 NLP tasks across three broad classes of problems (text classification, question answering, and sequence labeling). Our results show that transfer learning is more beneficial than previously thought, especially when target task data is scarce, and can improve performance even with low-data source tasks that differ substantially from the target task (e.g., part-of-speech tagging transfers well to the DROP QA dataset). We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task, and we validate their effectiveness in experiments controlled for source and target data size. Overall, our experiments reveal that factors such as data size, task and domain similarity, and task complexity all play a role in determining transferability.