Tag
Introduces VideoCoCo, an agentic dual-engine framework that uses executable Blender code as a chain-of-thought intermediate representation for physically-consistent video generation, achieving state-of-the-art scores on PhyGenBench and VBench-2.0.
ReDesign is an agentic framework that recovers editable layer hierarchies from raster images by selecting and composing specialized tools across modalities, introducing graceful verification to prevent error accumulation. It also introduces the FigmaEditReplay Benchmark for evaluating editability at scale, achieving high visual fidelity and superior editability over baselines.
Introduces EpiNarrate, an agentic framework that separates structured numerical reasoning from natural-language generation to produce grounded epidemiological narratives from ensemble projections.
O-VAD introduces a training-free agentic framework for industrial video anomaly detection that tracks object state evolution over time and reasons over temporal trajectories to identify abnormal objects, outperforming existing VLM and VAD methods on three datasets.
This paper introduces ChartCynics, an agentic dual-path framework that decouples perception from verification to robustly answer questions about misleading charts. It achieves state-of-the-art accuracy by using a diagnostic vision path and an OCR-driven data path, with a two-stage protocol for reasoning distillation and adversarial alignment.
Proposes AgentKGV, an agentic LLM-RAG framework with two-stage training (distillation SFT and trajectory-level GRPO) for verifying facts in knowledge graphs, achieving significant improvements on the T-REx benchmark while reducing retrieval calls.
HASE is a reinforcement-learning framework that co-evolves model weights, task solutions, and harness components (guidance and evaluation) in a unified agentic process, enabling a single 8B-parameter model to match the performance of much larger systems on text classification and alpha factor mining tasks.
Presents an agentic framework using general coding LLMs to autoformalize research-level mathematics into Lean 4 code, evaluated on Putnam problems and STOC conference papers.
VideoSearch-R1 introduces an agentic framework that iteratively retrieves videos and refines search queries using continuous latent space refinement and policy optimization, achieving state-of-the-art performance on video corpus moment retrieval and temporal grounding tasks.
This paper proposes Robust-TO, an agentic video understanding framework that integrates per-frame trustworthiness to address the Blind Trust Problem, achieving significant accuracy gains under realistic perturbations.
Robust-TO addresses the Blind Trust Problem in video reasoning by integrating per-frame trustworthiness into an agentic framework, improving accuracy under realistic perturbations through calibrated evidence weighting and reliability-aware reasoning.
Qwen-Image-Agent proposes a unified agentic framework that addresses the context gap in text-to-image generation by integrating planning, reasoning, searching, and memory mechanisms. It introduces IA-Bench for evaluation and achieves state-of-the-art performance.
OmniPath is a multi-modal agentic framework that combines OpenStreetMap network topology with aerial LiDAR data to audit wheelchair accessibility by analyzing physical barriers like slope and surface discontinuities at high resolution, validated against field surveys.
Eve, a new agentic framework from Vercel, is being compared to 'Next.js for agents' for its file-based approach to tools, skills, and evals, enabling rapid agent building with TypeScript.
Introduces ToolGrad, an agentic framework that generates, evaluates, and refines tool-use trajectories using textual 'gradients', achieving near 100% pass rate and lower cost for dataset generation. Accepted at ACL 2026.
RL-Index proposes a reinforcement learning-based agentic indexing framework that shifts reasoning from query time to the indexing stage by augmenting documents with LLM-generated rationales, improving retrieval effectiveness and reducing online latency.
AlloSpatial is an agentic framework that enhances spatial reasoning in foundation models by converting egocentric observations into structured allocentric representations, using cognitive mapping and tool-use reasoning. It improves performance by 5-18% on benchmarks and outperforms larger models through cold-start reinforcement learning.
ProSPy is a profiling-driven SQL-Python agentic framework for enterprise text-to-SQL that structures reasoning into four stages: automatic profiling, schema pruning, dialect-agnostic SQL interface, and Python-based analysis. It achieves execution accuracies of 60.15% and 60.51% on Spider 2.0-Lite and Spider 2.0-Snow with Claude-4.5-Opus, outperforming strong baselines.
QueryAgent-R1 is an agentic framework that bridges query generation and product retrieval in e-commerce using reinforcement learning and memory abstraction, improving query CTR by 2.9% and CVR by 3.1% in online tests.
A new Google paper introduces LEAP, an agentic framework that enables general LLMs to solve formal math problems by planning proofs and checking each step, raising performance from under 10% to 70% on the Lean IMO benchmark and solving all 2025 Putnam problems.