agentic-framework

Tag

Cards List
#agentic-framework

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Hugging Face Daily Papers ↗ · 2026-07-29 Cached

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.

0 favorites 0 likes
#agentic-framework

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

Hugging Face Daily Papers ↗ · 2026-07-28 Cached

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.

0 favorites 0 likes
#agentic-framework

EpiNarrate: Agentic Generation of Grounded Narratives from Epidemiological Scenario Projections

arXiv cs.CL ↗ · 2026-07-20 Cached

Introduces EpiNarrate, an agentic framework that separates structured numerical reasoning from natural-language generation to produce grounded epidemiological narratives from ensemble projections.

0 favorites 0 likes
#agentic-framework

O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning

Hugging Face Daily Papers ↗ · 2026-07-20 Cached

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.

0 favorites 0 likes
#agentic-framework

Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering

Hugging Face Daily Papers ↗ · 2026-07-14 Cached

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.

0 favorites 0 likes
#agentic-framework

AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge Graphs

arXiv cs.CL ↗ · 2026-07-13 Cached

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.

0 favorites 0 likes
#agentic-framework

Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions

arXiv cs.AI ↗ · 2026-07-07 Cached

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.

0 favorites 0 likes
#agentic-framework

Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics

arXiv cs.AI ↗ · 2026-07-01 Cached

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.

0 favorites 0 likes
#agentic-framework

VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement

Hugging Face Daily Papers ↗ · 2026-07-01 Cached

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.

0 favorites 0 likes
#agentic-framework

@_akhaliq: paper:

X AI KOLs Following ↗ · 2026-06-26 Cached

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.

0 favorites 0 likes
#agentic-framework

Confidence-Aware Tool Orchestration for Robust Video Understanding

Hugging Face Daily Papers ↗ · 2026-06-25 Cached

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.

0 favorites 0 likes
#agentic-framework

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

Hugging Face Daily Papers ↗ · 2026-06-25 Cached

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.

0 favorites 0 likes
#agentic-framework

OmniPath: A Multi-Modal Agentic Framework for Auditing Wheelchair Accessibility

arXiv cs.AI ↗ · 2026-06-24 Cached

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.

0 favorites 0 likes
#agentic-framework

@omarsar0: Eve does feel like the "Next.js for agents" as @rauchg puts it. You got to check it out!

X AI KOLs Following ↗ · 2026-06-23 Cached

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.

0 favorites 0 likes
#agentic-framework

@Zhongyi_Zhou_: ML optimizes via mathematical gradients; Loop Engineering needs textual "gradients"! Introducing ToolGrad: an agentic f…

X AI KOLs Timeline ↗ · 2026-06-17 Cached

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.

0 favorites 0 likes
#agentic-framework

RL-Index: Reinforcement Learning for Retrieval Index Reasoning

Hugging Face Daily Papers ↗ · 2026-06-15 Cached

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.

0 favorites 0 likes
#agentic-framework

AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models

Hugging Face Daily Papers ↗ · 2026-06-08 Cached

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.

0 favorites 0 likes
#agentic-framework

ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL

arXiv cs.CL ↗ · 2026-06-05 Cached

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.

0 favorites 0 likes
#agentic-framework

QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation

arXiv cs.CL ↗ · 2026-06-05 Cached

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.

0 favorites 0 likes
#agentic-framework

@rohanpaul_ai: Another great paper from Google. Shows general LLMs can solve formal math by planning proofs and checking each step. Ra…

X AI KOLs Following ↗ · 2026-06-04 Cached

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.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback