-
1. EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
Hugging Face Daily Papers / arXiv Recent AI/ML
20 小时前 · 2026/10/01 01:58
67 HF upvotes · 1 comments
来自 arXiv Recent AI/ML，主题偏「RAG/Memory、Eval/Data」。摘要显示它主要讨论 Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents helps, but simply adding web search tool can keep returning the same pages as solutions change. We introduce... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察知识工作、企业搜索、长期记忆和本地资料库产品的新实现路径。
读原文判断如果标题正好贴近当前产品方向，值得点开原文看方法和实验设置；泛读时先存为观察项。
RAG/MemoryEval/Data
Original abstract
Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents helps, but simply adding web search tool can keep returning the same pages as solutions change. We introduce EvoDuet, a bi-level optimization method that co-evolves solutions and search queries with fixed model parameters. At each iteration, a retrieval gate lets the LLM assess its knowledge gap and choose to retrieve new documents, reuse stored ones, or proceed without them. An inner loop refines queries and ranks documents by the solution scores they are predicted to yield; an outer loop generates candidates in parallel from these documents and records the evaluated outcomes for later searches. Across 21 optimization tasks with one candidate per iteration, EvoDuet raises OpenEvolve's normalized discovery gain from 74.1% to 78.0% with GPT-5.6-Luna and from 61.3% to 82.3% with Gemini-3.8-Flash, whereas Qwen3.5-9B does not benefit. Our best runs surpass the previously reported best scores on eight tasks, including Swap Reduction on Q20 and Rosetta, and match them on three more. EvoDuet also improves with other scaffolds (e.g., Top-K, EvoX) on Sums/Diffs and Denoising, demonstrating its applicability across evolutionary search scaffolds.
-
2. EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
39 HF upvotes · 1 comments · 2 GitHub stars
来自 Hugging Face Daily Papers，主题偏「Agent、Reasoning、Post-training/Alignment」。摘要显示它主要讨论 Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-model methods address this by training agents to predict future observations, at the cost of additional training... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察 agentic RL、工具调用、工作流自动化或软件代理能力是否出现新方法。
读原文判断如果你要找可复现 demo、开源工具或产品化线索，建议点开项目/GitHub；否则先看中文摘要即可。
AgentReasoningPost-training/AlignmentEval/DataCode
Original abstract
Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-model methods address this by training agents to predict future observations, at the cost of additional training and errors that compound when predictions are used for planning. However, for LLM agents operating in digital environments, much of this world knowledge is already internalized during pretraining, which shifts the problem from acquiring it to eliciting it. We argue that typical post-training provides little pressure for such elicitation, since supervision under a single goal at each visited state inadvertently drives policies to rely on superficial contextual habits. We introduce EVOKE, a post-training method that supplies this pressure through goal diversity at fixed states. Motivated by theory showing that an agent competent across diverse goals must encode a world model recoverable from its action preferences, EVOKE holds the environment state and interaction history fixed and ranks the same candidate actions under alternative goals, forcing action preferences to change, so that a policy relying on contextual habits or single-goal correlations cannot order them correctly. This implicitly elicits the policy's pretrained world knowledge to inform decisions. We evaluate EVOKE across diverse tasks in three backbones, demons...
-
3. Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
13 HF upvotes · 1 comments
来自 Hugging Face Daily Papers，主题偏「Agent、RAG/Memory、Reasoning」。摘要显示它主要讨论 Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent terminology and style. Existing single-LLM methods are largely sentence-level, and multi-agent systems often... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察 agentic RL、工具调用、工作流自动化或软件代理能力是否出现新方法。
读原文判断如果标题正好贴近当前产品方向，值得点开原文看方法和实验设置；泛读时先存为观察项。
AgentRAG/MemoryReasoningEval/DataAI Infra
Original abstract
Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent terminology and style. Existing single-LLM methods are largely sentence-level, and multi-agent systems often use static workflows that do not adapt to scene complexity or production context. We propose SMART, a Self-evolving Multi-Agent system for long-foRm subtitle Translation. During test-time training, SMART builds persistent series-level memory and translates a subset of sentences through a dynamic router and Mixture-of-Agents layer with tools for terminology verification, subtitle constraint validation, and contextual retrieval. A judge-refiner loop scores candidates and uses textual critiques to update agent prompts and routing policies without retraining the underlying LLMs. During test-time inference, the evolved configuration translates the remaining series. We also introduce Subtitle Arena, covering 14 genres, 2--198 episodes per series, production years 1959--2023, and 15 target locales, together with SubMQM, a subtitle-adapted MQM framework with seven dimensions and 19 error categories. SMART achieves the best overall MQM score in all 15 Subtitle Arena directions, reducing average penalty by 6.9% over the strongest competing agent system. On the public MuSC benchmark, SMART obtains the best model result across all fou...
-
4. CheatBench: Measuring Reward Gaming in AI Agents
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
1 comments · 11 GitHub stars
来自 Hugging Face Daily Papers，主题偏「Agent、Reasoning、Post-training/Alignment」。摘要显示它主要讨论 Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and controlled evaluations across the AI industry, agents trained to maximize reward have access... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察 agentic RL、工具调用、工作流自动化或软件代理能力是否出现新方法。
读原文判断如果你要找可复现 demo、开源工具或产品化线索，建议点开项目/GitHub；否则先看中文摘要即可。
AgentReasoningPost-training/AlignmentEval/DataCode
Original abstract
Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and controlled evaluations across the AI industry, agents trained to maximize reward have accessed unauthorized information, attempted to evade monitoring systems, and even breached sandbox protections to attack external systems. As agents become more capable, this behavior could pose increasingly serious risks. To measure this problem, we introduce CheatBench, a benchmark of cheating in AI agents across mathematical research, knowledge work, coding, visual tasks, and other domains. Its environments combine challenging assignments with opportunities to cheat, allowing researchers to study how agents pursue a goal when honest work is difficult. CheatBench supports comparisons across models and task categories, providing a testbed for measuring and reducing cheating as agents take on more consequential responsibilities. We publicly release CheatBench at https://cheatbench.ai
-
5. LoopVL: Recurrent Visual Intelligence
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
7 HF upvotes · 1 comments · 2 GitHub stars
来自 Hugging Face Daily Papers，主题偏「Reasoning、Multimodal、Post-training/Alignment」。摘要显示它主要讨论 We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-Loop computation to iteratively update a unified vision-language state through shared modules. We train LoopVL... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察模型推理、规划、验证器和复杂任务能力是否有可复用技术路线。
读原文判断如果你要找可复现 demo、开源工具或产品化线索，建议点开项目/GitHub；否则先看中文摘要即可。
ReasoningMultimodalPost-training/AlignmentEval/Data
Original abstract
We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-Loop computation to iteratively update a unified vision-language state through shared modules. We train LoopVL from scratch through language pre-training, multimodal training, and post-training. LoopVL outperforms a range of similarly sized and larger non-recurrent models on multimodal understanding and visual reasoning benchmarks. We also observe Visual Aha Moments in LoopVL, characterized by pronounced shifts in visual attention across loops. LoopVL provides practical evidence for recurrent vision-language modeling and offers an intuitive perspective on how shared parameters can support deeper multimodal computation over continuously evolving visual-language states.
-
6. OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
4 HF upvotes · 1 comments · 4 GitHub stars
来自 Hugging Face Daily Papers，主题偏「Agent、Reasoning、Multimodal」。摘要显示它主要讨论 Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized interfaces, manipulating scientific objects, and producing verifiable results. We t... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察 agentic RL、工具调用、工作流自动化或软件代理能力是否出现新方法。
读原文判断如果你要找可复现 demo、开源工具或产品化线索，建议点开项目/GitHub；否则先看中文摘要即可。
AgentReasoningMultimodalEval/DataAI Infra
Original abstract
Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized interfaces, manipulating scientific objects, and producing verifiable results. We thus introduce OSWorld-Science, a benchmark and evaluation environment that combines scientifically meaningful tasks, artifact-based evaluation, and an efficient agent harness for studying computer use in the scientific domain. The benchmark contains 12 VLMs and 146 high-quality tasks across several scientific domains and software configurations, covering workflows such as molecular drawing and retrosynthesis, pathology image analysis, statistical computing, and physical simulation. Tasks are developed through expert proposals and iterative human--AI co-design, with selection guided by scientific value and difficulty. Task-specific execution-based evaluators inspect application states and generated artifacts, including molecular structures, segmentation masks, plots, and numerical results, and award partial credit for incomplete outcomes. Our special harness integrates model adapters, interaction-loop control, and trajectory logging to support comparisons of models and interaction strategies. Our results show that current state-of-the-art VLMs with a strong harness still face challenges in addressing key questions in the sc...
-
7. Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
6 HF upvotes · 1 comments
来自 Hugging Face Daily Papers，主题偏「Agent、RAG/Memory、Post-training/Alignment」。摘要显示它主要讨论 Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly constrain their execution. We call the ability to benefit from useful guidance while overriding unreliable guidan... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察 agentic RL、工具调用、工作流自动化或软件代理能力是否出现新方法。
读原文判断如果标题正好贴近当前产品方向，值得点开原文看方法和实验设置；泛读时先存为观察项。
AgentRAG/MemoryPost-training/AlignmentEval/DataAI Infra
Original abstract
Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly constrain their execution. We call the ability to benefit from useful guidance while overriding unreliable guidance thinking outside the box. We introduce Box^2-Bench, which holds the model and task fixed while varying workflow reliability to isolate how models regulate their reliance on guidance. On Box^2-Bench, frontier models often benefit from reliable guidance but remain vulnerable when it is misleading or becomes unreliable. To test whether this capability can be learned, we train two open-weight models using bad workflows, reserving good workflows for evaluation. We explore two complementary training strategies: counterfactual supervised fine-tuning improves robustness, while outcome-based reinforcement learning can shift the balance toward greater use of helpful workflows. We further find that this behavior extends beyond workflows to other forms of external information, improving peer correction and robustness to corrupted memory. Together, our results identify selective reliance on fallible external information as a dimension of agent reliability not captured by task performance alone.
-
8. CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
2 HF upvotes · 1 comments
来自 Hugging Face Daily Papers，主题偏「Agent、Reasoning、Multimodal」。摘要显示它主要讨论 Ultra-long video temporal grounding requires balancing long-range evidence search with fine-grained event understanding under a limited visual budget, yet existing agentic methods still rely largely on predefined policies and tool capabilities. Motivated by th... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察 agentic RL、工具调用、工作流自动化或软件代理能力是否出现新方法。
读原文判断如果你要找可复现 demo、开源工具或产品化线索，建议点开项目/GitHub；否则先看中文摘要即可。
AgentReasoningMultimodalEval/DataAI Infra
Original abstract
Ultra-long video temporal grounding requires balancing long-range evidence search with fine-grained event understanding under a limited visual budget, yet existing agentic methods still rely largely on predefined policies and tool capabilities. Motivated by this, we propose a novel policy-tool coevolution framework that jointly evolves high-level policies and executable media tools from the agentic reasoning trajectories of a VLM, forming a reusable skill without updating model parameters. During evolution, an external skill updater distills transferable task experience in long-video temporal grounding, accordingly refining the orchestration of long-range image-based and fine-grained video-based observations. Alongside these policy updates, the updater employs its coding capabilities to upgrade existing tools or create new ones, adapting the tools to long-video evidence acquisition. Equipped with the evolved skill, the VLM autonomously orchestrates tools under the guidance of the evolved policy, coordinating image and video observations for agentic inference without relying on a separate, stronger planning model. Extensive experiments spanning five benchmarks and three VLMs show that policy-tool coevolution consistently improves temporal grounding accuracy in ultra-long videos while reducing visual token cost at inference, and that the evolved skill yields substantial performan...
-
9. CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
1 HF upvotes · 1 comments · 1 GitHub stars
来自 Hugging Face Daily Papers，主题偏「Agent、Eval/Data、Code」。摘要显示它主要讨论 Software development requires more than editing code: developers repeatedly run software, interact with its interfaces, visually inspect its behavior, and use these observations to decide what to change next and whether a change works. Existing coding agents a... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察 agentic RL、工具调用、工作流自动化或软件代理能力是否出现新方法。
读原文判断如果你要找可复现 demo、开源工具或产品化线索，建议点开项目/GitHub；否则先看中文摘要即可。
AgentEval/DataCode
Original abstract
Software development requires more than editing code: developers repeatedly run software, interact with its interfaces, visually inspect its behavior, and use these observations to decide what to change next and whether a change works. Existing coding agents and computer-use agents are largely studied in isolation, leaving this integrated development process underexplored. Diagnosing a runtime interaction failure requires agents to connect visual observations with the responsible code, then use the application again to verify the repair. We introduce CUA-SWE, a benchmark, environment, and evaluation pipeline for software engineering with computer use. Beyond studying how GUI feedback supports diagnosis and repair, we ask whether agents can complete software engineering tasks when required specification or operational information is available only through the running application's visual interface. CUA-SWE spans four software engineering domains and requires agents to modify code and configuration, execute commands, interact with running software, and inspect visual feedback within the same task. Each task includes deterministic, task-specific tests that verify whether the resulting software satisfies the requirements and preserves specified behavior. Our evaluation characterizes how frontier agents combine source-level execution with application screenshots and graphical intera...
-
10. LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
1 HF upvotes · 1 comments
来自 Hugging Face Daily Papers，主题偏「RAG/Memory、Reasoning、Multimodal」。摘要显示它主要讨论 Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform temporal compression severely dilutes fine-grained acoustic and visual evidence. We introduce LEAP,... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察知识工作、企业搜索、长期记忆和本地资料库产品的新实现路径。
读原文判断如果标题正好贴近当前产品方向，值得点开原文看方法和实验设置；泛读时先存为观察项。
RAG/MemoryReasoningMultimodalEval/DataAI Infra
Original abstract
Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform temporal compression severely dilutes fine-grained acoustic and visual evidence. We introduce LEAP, a framework where the model retrieves its own evidence without placing the whole recording in one context. LEAP divides a recording into fixed-duration blocks, applying a lightweight localization pass to each block to score short candidate windows. The highest-ranked windows are pooled and re-encoded in a single bounded answer pass. Consequently, the answer input and peak context remain independent of the recording duration. By decoupling evidence localization from reasoning, our framework can localize candidate temporal windows over pre-computed transcripts without decoding media frames, while preserving fine-grained visual and non-speech evidence by routing the final answering pass over raw audio-visual streams. LEAP trains both stages: a localization LoRA improves the selected windows, and an answer LoRA improves the answers read from the same windows. The block grid natively supports causal queries, enabling LEAP to support streaming inference without streaming-specific training. Across several AVQA benchmarks, LEAP improves over the Qwen3-Omni-30B-A3B baseline by 4.5-16.8%, and transfers to a second omni-modal backbon...
-
11. Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
1 HF upvotes · 1 comments
来自 Hugging Face Daily Papers，主题偏「Reasoning、Eval/Data、Code」。摘要显示它主要讨论 Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and batching. We identify an overlooked factor: the hidden injection of the current date into system prompts, which users cannot control and which ch... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察模型推理、规划、验证器和复杂任务能力是否有可复用技术路线。
读原文判断先作为日更雷达记录；除非与你当前研究/产品问题高度相关，不必立刻精读全文。
ReasoningEval/DataCodeRobotics
Original abstract
Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and batching. We identify an overlooked factor: the hidden injection of the current date into system prompts, which users cannot control and which changes every day. Across 9 recent LLMs and 6 datasets spanning multiple-choice QA (MCQA), math reasoning, code generation, and machine translation, performance varies solely with the current date, with deltas of up to 6% on MCQA, 14% on math reasoning, 7% on code generation, and 2.84 BLEU on machine translation. Model rankings also shift, affecting leaderboards. This date effect exceeds other sources of non-determinism, such as batch size and numerical precision. Standard prompting techniques -- chain-of-thought and few-shot prompting -- do not reduce the sensitivity; chain-of-thought even amplifies it. Our findings underscore the need for careful evaluation protocols to ensure reproducibility and fair comparisons in LLM research.
-
12. Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds
Hugging Face Daily Papers
14 小时前 · 2026/10/01 08:00
1 comments
来自 Hugging Face Daily Papers，主题偏「Agent、RAG/Memory、Multimodal」。摘要显示它主要讨论 Persistent spatial memory enables embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved, including during navigation, making remembered locations unreliable by the time an agent arrives. Despite ad... 先把它当作时效信号看：判断它是否正在影响 agent、RAG、多模态、post-training、评测或 AI infra 的产品/研究方向。
为什么值得看适合观察 agentic RL、工具调用、工作流自动化或软件代理能力是否出现新方法。
读原文判断如果你要找可复现 demo、开源工具或产品化线索，建议点开项目/GitHub；否则先看中文摘要即可。
AgentRAG/MemoryMultimodalEval/DataAI Infra
Original abstract
Persistent spatial memory enables embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved, including during navigation, making remembered locations unreliable by the time an agent arrives. Despite advances in memory retrieval and state prediction, accounting for continued hidden world evolution and revising beliefs under limited visibility remain challenging. We study Evolving-World Navigation, where agents infer target locations from intermittent observations, predict their states at inspection time, and revise beliefs using visual evidence. We propose EvolvingNav, which constructs a time-indexed belief from timestamped 3D object histories through a structured persistence-relocation model. The belief distinguishes persistence at the last observed location from relocation to alternative locations and retains probability mass outside the known candidate set. An event-driven filter propagates the current belief as time elapses, forecasts target occupancy at candidate inspection times, and incorporates new RGB-D evidence. Negative observations downweight location hypotheses according to calibrated, visibility-conditioned detection probabilities, while evidence tracking prevents repeated use of the same observations. A frozen, zero-shot vision-language controller uses the updated belief to choose actions and replan. We fu...
Using cached daily papers because the latest fetch failed.
