每日 AI 论文精选

A 150M-parameter reasoning model using recurrent latent reasoning and in-context learning achieves a new cost-accuracy frontier on ARC-AGI-1.

2608.09888 · ▲ 593 · Code

Macaron-V1 is an open agent-model family that uses a Mixture-of-LoRA architecture and recursive self-improvement to enable continual learning and collaboration across specialized tasks.

2608.09819 · ▲ 328

Unsupervised on-policy self-distillation improves large language models by using internal consistency and majority-vote pseudo-solutions to correct confident errors without external supervision.

2608.06296 · ▲ 194

OpenART introduces a scalable red-teaming arena with evolving stateful environments to evaluate long-horizon AI agent safety, using the EMHA attack policy to expose increasing failure rates as task complexity grows.

2608.00677 · ▲ 182 · Code

Combodied Agents integrate digital and embodied tools into a closed-loop framework that models individual human-state trajectories over time to provide proportionate, consent-aware support.

2608.10915 · ▲ 181

Spark-to-Paper is a lightweight, composable workflow inside coding assistants that generates research papers by separating planning from reporting, enforcing evidence-based claim revision, and using integrity checks to reduce fabrication.

2608.11924 · ▲ 176 · Code

Latent-to-4D enables reusable direct 4D generation from video diffusion latents via alignment with a pretrained decoder and spatiotemporal attention, transferring across generators without retraining.

2608.10744 · ▲ 171 · Code

SWE-Bench ProMax is a rigorously curated multilingual benchmark of large-scale code refactoring tasks that reveals substantial unsolved challenges for current AI coding agents.

2608.09802 · ▲ 126

Agentic systems can achieve open-ended improvement through multi-component co-evolution that progressively removes fixed human constraints across agents, environments, and evolution mechanisms.

2608.10299 · ▲ 124 · Code

SimWAM trains a lightweight action planner using video generation as a training signal, enabling efficient trajectory prediction without future generation at inference and supporting reinforcement learning optimization.

2608.07468 · ▲ 102 · Code

Stronger models can build inference-time harnesses that substantially improve weaker models' task performance without parameter updates by offloading reasoning into structured code and routing.

2608.12307 · ▲ 97

Encrypted reasoning traces shared across sessions and models can be intercepted and injected into weaker models to extract proprietary reasoning, private data, hidden hazards, and hidden prompts.

2608.09867 · ▲ 96

AgentOPSD uses recursive Bayesian belief updates over turn-level log-probability gaps to assign credit in long-horizon agentic reinforcement learning without extra critics or rollouts.

2608.05987 · ▲ 92 · Code

We present Ouroboros, a self-developing agent harness whose tools, prompts, context assembly, and core implementation improve through reviewed commits that become the runtime for later work. Core evolution proceeds in two modes. In recursive free evolution, improvement is itself a task, and completing one evolution cycle can schedule the next. In experience-driven core evolution, ordinary work and social interaction expose bugs, rough edges, and inefficient context construction that lead to reviewed structural changes. On Terminal-Bench 2.1, an Opus 5 run scores 86.74%, the best result reported on the benchmark. On OSWorld-Verified, an Opus 5 run reaches 90.69%, exceeding the best previously reported score. A five-rollout CL-Bench campaign achieves a normalized reward of 0.2301, setting a new state of the art. Hope is the longest-running publicly documented Ouroboros deployment. It is a 161-day living agent experiment in free evolution under governed human communication across seven surfaces. Human interaction surfaces faults and generates proposals, but the agent decides which changes to pursue. Because a self-developing agent may rewrite its own code and select new model APIs, operational safety becomes a primary design problem: guardrails must remain authoritative under evolutionary and public social pressure. Benchmark campaigns use frozen system snapshots, while Hope continues live evolution on a separate lineage.

2608.08311 · ▲ 84 · Code

Mechanist is an autonomous agentic system that uses AI to discover and control the mechanisms underlying model intelligence, generating hypotheses, performing causal interventions, and improving safety and performance.

2608.12036 · ▲ 73 · Code

SkillZip compresses reusable procedural skills into contract-preserving, executable graph units to enable efficient retrieval and expansion under limited context budgets.

2608.05604 · ▲ 72

Researchers introduce a benchmark and open reward models to evaluate and improve vision-language judges for computer-using agent trajectories, revealing systematic leniency biases and offering cost-effective alternatives.

2607.28609 · ▲ 71 · Code

Redesigning a MEG-to-audio retrieval model with spherical harmonics, source-space mapping, and input interventions reveals that narrative speech structure, acoustic onsets, and intensity drive retrieval while reducing parameters.

2608.01481 · ▲ 69 · Code

WorldClaw is an agentic coarse-to-fine framework that generates large-scale editable 3D worlds from text by combining planning agents, semantic layouts, reusable assets, and render-based refinement.

2608.05248 · ▲ 68

Reinforcement learning enables stable multi-task reasoning in large language models through sparse, near-orthogonal parameter updates, unlike supervised fine-tuning which suffers from task conflicts, motivating a decoupled Parallel-RL training approach.

2608.03573 · ▲ 51 · Code

Agent Memory Distillation improves small language model tool-use performance by transferring structured hierarchical memory from a large teacher agent without additional training.

2608.07169 · ▲ 47 · Code

The study introduces a video benchmark requiring global spatial reasoning across long videos and reveals that vision-language models struggle to build consistent global scene representations despite strong local perception.

2608.05747 · ▲ 46

A rest-state framework reconstructs articulated objects from a single closed configuration by fusing vision-language outputs into consistent part meshes and validating synthesized motion hypotheses via geometric consistency.

2607.27749 · ▲ 44

EnvACE trains large language model agents via internal world rehearsal instead of external environments, improving long-horizon tool use through joint optimization of action and simulated response.

2608.06197 · ▲ 43 · Code

Motif 3 is a large sparse mixture-of-experts language model using grouped differential latent attention and specialized training techniques to achieve strong reasoning, coding, and long-context performance.

2608.09119 · ▲ 43

Effective multimodal agent training is improved by selecting diverse environments via ability-aware selection and structuring difficulty through hierarchical curriculum learning.

2608.03571 · ▲ 42 · Code

UniME-R1 improves multimodal retrieval by generating retrieval-centric reasoning guided by initial candidate feedback rather than query-only explanations.

2608.06060 · ▲ 40 · Code

MatrAIx is a large-scale simulated-user evaluation framework that uses diverse persona records and interactive environments to test AI systems across many domains.

2608.04205 · ▲ 34 · Code

Economic world models are generative agent-based simulations organized by a six-level capability ladder to build high-fidelity economic sandboxes and AI training substrates.

2608.06020 · ▲ 34 · Code

DataSpace is a benchmark for evaluating data agents that generate verifiable tabular results from heterogeneous organizational workspaces, revealing significant accuracy gaps across frontier models and agent harnesses.

2608.03451 · ▲ 33 · Code

A deterministic screen-activity compiler builds auditable agent memory from raw capture, sharply reducing context size while improving answer accuracy over LLM summaries, and it measures routine overhead and recurrence to bound agent inference costs.

2608.05784 · ▲ 28 · Code

KVAE tokenizers for audio, image, and video achieve competitive reconstruction and generation quality compared to leading open-source alternatives while providing training details and open-source code.

2608.05798 · ▲ 28 · Code

Mendel Gödel Machine improves self-improving coding agents by using multi-trajectory mutations and cross-lineage hybridization to accelerate convergence and boost performance.

2608.07645 · ▲ 26 · Code

W2-VLA improves fine-grained robot manipulation by forecasting future wrist interactions via a latent interface between vision-language and wrist prediction, supported by structured progress annotations.

2608.05369 · ▲ 26 · Code

The study introduces a benchmark and formalizes narrative commitment preservation to evaluate long-horizon logical consistency in interactive storytelling with large language models.

2608.08160 · ▲ 25 · Code

Business Arena evaluates LLM agents running a realistic cross-border shop, revealing large performance gaps versus human strategies and enabling detailed attribution of business decisions.

2608.08621 · ▲ 20 · Code

Integrating interpretability as a training constraint yields scalable, disentangled representations that enable attribution, retrieval, and steering without retraining.

2608.07594 · ▲ 19 · Code

A new benchmark called VibeLifeBench evaluates long-horizon proactive agents across simulated multi-week everyday tasks, revealing that current frontier models perform poorly.

2608.10875 · ▲ 17 · Code

Ex-Omni-2D is an omni-modal dialogue framework that produces coordinated text, speech, and video responses via a visual thought plan and a distilled streaming video generator.

2608.10720 · ▲ 15 · Code

Open multilingual translation models are improved via group relative policy optimization with reference-free quality rewards and checkpoint interpolation, surpassing strong open and proprietary baselines.

2608.10812 · ▲ 12 · Code

Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan future actions, and determine when it has reached a navigation goal under partial observability. Although recent VLA models offer a promising perception-to-action paradigm, adapting them to aerial navigation remains challenging due to limited historical context, short planning horizons, and unreliable implicit termination. To address these challenges, we propose DreamFly, a diffusion-based aerial VLN framework built on Dream-VLA. DreamFly introduces a causally aligned historical memory that augments the current visual representation using only observations preceding the current decision step, enabling temporal reasoning without future information leakage. We further formulate navigation as receding-horizon diffusion planning, where the policy predicts a $K$-step action chunk but executes only the first action before replanning. This plan-$K$, execute-one strategy uses future actions as auxiliary planning targets while preserving closed-loop visual feedback. Finally, LiteStop estimates the stop probability directly from action logits at the initial all-mask state, decoupling explicit termination from action generation. Experiments on the OpenFly benchmark demonstrate consistent improvements in seen and unseen environments. DreamFly achieves 32.04%/29.46% SR and 28.22%/23.54% SPL on the test-seen/test-unseen splits, respectively, outperforming all compared methods on both metrics while attaining the lowest navigation error. These results demonstrate the effectiveness of jointly modeling historical context, future action structure, and explicit termination for aerial VLN.

2608.12308v1

Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, and related training-time methods. In this paper, we ask whether such transfer can instead occur at test time. We study strong-to-weak scaffolding: whether a stronger builder model can construct inference-time harnesses that help a weaker target model solve tasks more reliably without any parameter updates. Using four representative Theory-of-Mind benchmarks, each builder model uses 5% of the data as a validation set to iteratively refine its harness over multiple rounds, after which the finalized harness is evaluated on the full test set. Empirically, this form of test-time capability transfer is highly effective, nearly doubling average target-model performance from 0.49 to 0.91. Our analysis shows that the gains come primarily from offloading unstable model reasoning into deterministic code, benchmark-specific routing, and strict answer-format enforcement, rather than from encouraging the target model to reason more extensively or sample more broadly. We further find that builder-model reasoning effort improves harness quality monotonically, platform effects are modest relative to the builder model's own capability, and weaker target models receive the largest gains. These results suggest that inference-time harness design is an important complement to conventional training-time distillation, enabling strong models to transfer cognitive structure to weaker models without retraining.

2608.12307v1

Safe offline RL typically assumes access to dense per-step cost annotations, but in practice supervisors provide only trajectory-level stop-feedback: a binary signal at the first unsafe transition, with no per-step attribution. We frame this as a temporal credit assignment problem and propose the Redistribution-based Cost Inference (RCI) framework, which converts sparse stop-feedback into dense per-step costs via return decomposition, then trains a constrained offline policy on the augmented dataset. We show that return-equivalent redistribution preserves the feasible policy set and the optimal Lagrangian in a CMDP, establishing that the transformation is lossless in theory while yielding better-conditioned cost critic learning in practice. Experiments on highway driving and robotic manipulation demonstrate substantially lower violation rates than sparse and classifier-based baselines, with robustness to heterogeneous dataset compositions and label noise.

2608.12306v1

Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. However, DML construction typically relies on expert interpretation of technical documentation, limiting scalability for complex systems. This study presents a framework for automated construction of DML models from system descriptions and their representation as Knowledge Graphs (KG-DML), using Retrieval-Augmented Generation and Large Language Models as enabling tools. Building on prior work with small-scale systems, the framework extends automated KG-DML construction and evaluation to substantially larger and more complex systems. Model construction proceeds across the DML hierarchy using targeted retrieval while preserving functional dependencies and explicit logical relationships. The resulting KG-DML supports diagnostic reasoning, safety assessment, upward failure propagation, and downward dependency tracing. A multi-level validation methodology evaluates layer-specific precision and recall, logical gate consistency, and overall structural integrity. Application to the Low-Pressure Coolant Injection system of a decommissioned Boiling Water Reactor demonstrates consistent reconstruction across repeated runs. The results show that automated KG-DML construction can transform technical documentation into executable functional models for diagnostic and reliability analysis.

2608.12304v1

Creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key challenge is the absence of a structured video representation that is both faithful to film content and directly usable for agentic reasoning and manipulation. To address the challenge, we propose the Agentic Video Auto-Encoder (AVA-Encoder), a framework for learning agent-native video representations via agentic auto-encoding. AVA-Encoder transforms a video into a knowledge graph (KG) representation and then reconstructs it back into video. Its hierarchy and state nodes store structured text, while a linked asset layer holds generated images, audio, and video. Typed edges preserve the relations between these text descriptions and assets in a form that agents can easily understand, query, and edit. The video reconstruction differences drive a textual-gradient optimization framework, which expresses evaluation feedback as natural-language update directions for Data-Independent Encoding Policy Pseudo-Training in the outer loop and optional Data-Dependent KG Representation Refinement in the test-time inner loop. Extensive experiments show that AVA-Encoder improves by 20.7 percentage points over the strongest external baseline. In the controlled policy-only setting, its pseudo-trained shot-level Agentic Video Encoder policy also outperforms a carefully human-tuned policy while using 74.3% fewer system-prompt tokens. We release the complete AVA-Encoder framework, a reliable agentic video reconstruction benchmark, and the first dataset of high-quality film KG representations.

2608.12313v1

Large language models can extract richer signals from financial news than fixed sentiment lexicons, and recent work has explored feeding such signals into portfolio construction. We study an uncertainty-aware construction that feeds model-predicted risk -- decomposed into aleatoric and epistemic components -- directly into the covariance matrix of portfolio allocators, rather than treating portfolio risk as fixed or adjusting only expected returns. We evaluate the pipeline on Russell 2000 equities under three stock-selection regimes: a pure-alpha trigger that isolates abnormal stock moves not explained by macro indicators, a pure-beta trigger that captures macro-indicator moves before the stock itself fires, and a beta trigger in which both channels agree. Across the full holding-period grid, the separated pure-alpha and pure-beta legs usually dominate the beta intersection on Sharpe and return. Two horizons are especially informative. At one day, pure beta can work under low and moderate transaction costs because it captures immediate lead-lag spillovers from liquid macro and sector indicators into exposed small-cap stocks, but this advantage disappears at 100 bps when turnover and microstructure noise dominate. At 40 days, pure beta works for a different reason: slower macro repricing overtakes the firm-specific pure-alpha channel. The strongest conservative row is pure beta with GPT-4o mini sentiment, a Student-t target, a 40-day holding period, and risk parity allocation, reaching Sharpe 2.33 at 100 bps. The results suggest that stock-selection regime and allocator choice matter at least as much as the sentiment model, and that separating firm-specific and macro-exposure triggers is more informative than requiring both to fire simultaneously.

2608.12283v1

Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the token generation budget, i.e., the maximum tokens a model may produce, across seven levels (64--4,096), evaluating four models on three reasoning benchmarks (56,476 inferences). We report four findings: (i) 3--19% of items exhibit non-monotone behavior (accuracy decreasing with more budget), even after controlling for truncation, and this phenomenon is model-specific (cross-model overlap: 6--14%). (ii) Model rankings reverse across budgets on all benchmarks ($p {<} 0.01$, McNemar). (iii) Oracle analysis reveals model complementarity up to $+27.8$pp, most pronounced at constrained budgets. (iv) A budget-aware router captures 14.1% of the oracle gap cross-domain; budget features help within-domain ($+1.6$ to $+5.7$pp) but are domain-specific and hurt transfer ($-1.2$pp). These results argue for budget-conditioned evaluation protocols.

2608.12150v1

General-purpose large language models (LLMs) have recently been reported to match or exceed specialized clinical AI tools on medical benchmarks, but such comparisons draw on a narrow set of systems and on benchmarks developed largely in high-income settings. We evaluate VITA, a retrieval-augmented generation (RAG) system purpose-built for contextual knowledge retrieval in India and other low- and middle-income (LMIC) settings. VITA retrieves from a curated corpus of disease-specific guidelines, India-specific antimicrobial resistance data, national formulary constraints, and resource-limited care protocols; its architecture and corpus are proprietary, but the benchmark, the physician-written rubrics, and our full response and scoring outputs are public for independent verification. On 4,023 English-language HealthBench questions (80.5% of the benchmark), scored with a GPT-4.1 judge, VITA ranked first with 51.9% of possible rubric points, ahead of GPT-5.4 (46.1%), o4-mini (44.3%), Gemini 3.1 Pro (42.6%), and Claude Sonnet 4.6 (37.3%), and scored highest on 45.4% of questions. To test robustness to newer models and judge lineage, a 500-question subset was re-run against current-generation models (GPT-5.5, Claude Opus 4.8, Gemini 3.5 Pro, Grok 4.3) and graded by a neutral open-weight judge (DeepSeek-V4-Pro) sharing no lineage with any system tested. Here the gap narrowed to parity: VITA and GPT-5.5 were statistically indistinguishable on mean per-question score, while VITA led on points-weighted score and won the most questions. VITA's advantages in accuracy and completeness persisted under the neutral judge; its communication scores were lower. These results indicate that a purpose-built clinical RAG system remains competitive with frontier LLMs on an open benchmark, consistent with corpus specificity as a design variable that improves grounding at some cost to communication polish.

2608.12138v1

Previsualization is an intermediate layer between ideas and production in film, games, architecture, and urban design. It lets creators iteratively refine scenes, actions, cameras, and spatial-temporal dynamics. Yet existing generative methods rely on simple prompts to jointly control all of these factors through one-shot image or video synthesis, offering weak controllability and limited support for iterative editing. Fundamentally, a world comprises multiple elements with geometry, appearance, and other attributes, together with cameras. Different frames are produced through local modifications or recombinations of this shared state, which is otherwise largely reused. Therefore, we argue that the missing component is an explicit and persistent working state. To address this, we present StateFlow, a state-centric framework for generative previsualization. Rather than generating videos in one shot, StateFlow uses an editable 3D world to organize scene structure, evolution, and cameras, while off-the-shelf video models enhance visual quality when higher fidelity is desired. This world is maintained as a persistent structured 3D state of scene elements and camera configurations, serving as the core working representation for previsualization. Built on this insight, StateFlow has three stages to construct, evolve, and access the world state. State construction lifts generated 2D content into a coherent 3D world through prior-guided, conflict-aware dual-view initialization, while State evolution translates user intent into structured state transitions while preserving world memory, avoiding full-scene regeneration for each edit. State access uses render-feedback reflection to refine camera plans into visually feasible trajectories, avoiding reliance on VLM semantics alone. Experiments show that StateFlow produces high-quality 3D worlds for video creation and game-like prototyping.

2608.12314v1

High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative sampling. Existing efficient methods mainly distill pretrained models into few-step samplers, a challenging process that depends heavily on teacher-model quality. In this paper, we introduce XYZFlow, a framework that rethinks efficient generation through multidimensional scaling of flow matching. Unlike single-step mappings, XYZFlow enhances expressivity by making probability paths more identifiable and learnable through structured multidimensional conditioning. We view autoregressive modeling as implicit flow straightening, where richer context reduces trajectory ambiguity. XYZFlow realizes this idea through two orthogonal dimensions: temporal scaling, which uses non-Markovian conditioning on the full denoising history; and spatial scaling, enabled by Next Shortcut Prediction, which sequentially generates patches using preceding patches' denoising trajectories as priors. Experiments show that XYZFlow achieves state-of-the-art performance, with 7.2-8.5X teacher speedups and competitive FID, while Next Shortcut Prediction delivers superior quality-latency trade-offs over model scaling or step reduction.

2608.12276v1