agentic-reasoning

Tag

Cards List
#agentic-reasoning

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

arXiv cs.CL · 2026-06-24 Cached

AGORA is a new benchmark for evaluating large language models on archive-grounded reasoning tasks across workplace documents, comprising 362 questions over 9,664 real documents. The strongest model achieves only 59.4% accuracy, highlighting substantial room for improvement.

0 favorites 0 likes
#agentic-reasoning

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Hugging Face Daily Papers · 2026-06-12 Cached

Nemotron 3 Ultra is a 550B parameter hybrid Mamba-Attention mixture-of-experts language model, pre-trained on 20T tokens, extended to 1M context, and post-trained with SFT, RL, and MOPD. It achieves up to 6x higher inference throughput than state-of-the-art LLMs with comparable accuracy, and is open-sourced.

0 favorites 0 likes
#agentic-reasoning

PhotoCraft: Agentic Reasoning with Hierarchical Self-Evolving Memory for Deep Image Search

arXiv cs.CL · 2026-06-03 Cached

PhotoCraft proposes a training-free hierarchical memory system for photo-search agents, integrating working, episodic, and semantic memory to maintain long-horizon context and transfer knowledge across tasks, achieving up to 18.5% improvement on DISBench.

0 favorites 0 likes
#agentic-reasoning

Adaptive Latent Agentic Reasoning

arXiv cs.CL · 2026-06-03 Cached

This paper introduces Adaptive Latent Agentic Reasoning (ALAR), a dual-mode framework for LLM agents that uses compact latent reasoning for routine turns and selectively escalates to explicit chain-of-thought for harder decisions, achieving up to 84.6% token reduction while maintaining task accuracy.

0 favorites 0 likes
#agentic-reasoning

DAR: Deontic Reasoning with Agentic Harnesses

Hugging Face Daily Papers · 2026-06-03

This paper introduces DAR (Deontic Agentic Reasoning), an agentic framework enabling LLMs to interactively query statutes and policies for legal/regulatory reasoning tasks. Evaluated on DeonticBench, results show agentic harnesses improve frontier models but can degrade weaker models on numerical tasks while consuming more tokens.

0 favorites 0 likes
#agentic-reasoning

CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming

arXiv cs.CL · 2026-05-26 Cached

CP-Agent presents a calibrated risk-controlled approach for feedback-driven competitive programming using large language models, achieving significant improvements on benchmarks without parameter updates.

0 favorites 0 likes
#agentic-reasoning

SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent

Hugging Face Daily Papers · 2026-05-23 Cached

This paper proposes SAM, a state-adaptive memory framework that dynamically manages interaction histories for long-horizon agentic reasoning, enabling intent-driven recall without retraining the backbone model. It outperforms strong baselines across multiple benchmarks like BrowseComp and HLE.

0 favorites 0 likes
#agentic-reasoning

@reach_vb: GPT-5.5 cranking out 30k lines of QML for the Omarchy 4 branch + nailing subtle agentic reasoning!!

X AI KOLs Following · 2026-05-22 Cached

OpenAI's GPT-5.5 model shows significant improvements in complex agentic tasks and code generation, outperforming previous versions and competing models like Claude Opus.

0 favorites 0 likes
#agentic-reasoning

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

Hugging Face Daily Papers · 2026-05-21 Cached

Introduces SR²AM, a framework for efficient agentic reasoning via self-regulated simulative planning, achieving competitive performance with models 20-30x larger while using 26-95% fewer reasoning tokens.

0 favorites 0 likes
#agentic-reasoning

CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning

Hugging Face Daily Papers · 2026-05-19 Cached

CopT introduces a contrastive on-policy thinking framework for LLMs that generates draft answers first, then uses contrastive verification and dynamic thinking to improve accuracy while reducing token consumption, achieving up to 23% higher accuracy and 57% lower token usage on math, coding, and agentic reasoning tasks.

0 favorites 0 likes
#agentic-reasoning

VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation

Hugging Face Daily Papers · 2026-05-15 Cached

VideoSeeker introduces a paradigm for instance-level video understanding that integrates agentic reasoning with visual prompts, achieving superior performance through automated data synthesis and reinforcement learning, outperforming GPT-4o and Gemini-2.5-Pro.

0 favorites 0 likes
#agentic-reasoning

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both

Hugging Face Daily Papers · 2026-05-14 Cached

ATLAS presents a visual reasoning framework that combines agentic operations and latent representations using functional tokens, enabling efficient training via next-token prediction and reinforcement learning while avoiding intermediate image generation.

0 favorites 0 likes
#agentic-reasoning

Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization

Hugging Face Daily Papers · 2026-05-12 Cached

This paper proposes an exploration-aware reinforcement learning framework that enables LLM agents to adaptively explore only when uncertainty is high, improving performance on text-based and GUI-based benchmarks.

0 favorites 0 likes
#agentic-reasoning

Tools as Continuous Flow for Evolving Agentic Reasoning

arXiv cs.AI · 2026-05-11 Cached

This paper introduces FlowAgent, a novel framework that reconceptualizes tool chaining as continuous trajectory generation using conditional flow matching to improve robustness in long-horizon agentic reasoning.

0 favorites 0 likes
#agentic-reasoning

Characterizing AlphaEarth Embedding Geometry for Agentic Environmental Reasoning

arXiv cs.CL · 2026-04-22 Cached

Analyzes the 64-D embedding manifold of Google AlphaEarth across 12.1M U.S. samples, shows non-Euclidean structure and poor vector arithmetic, then builds an agentic system with geometry-aware tools that outperforms parametric baselines on environmental queries.

0 favorites 0 likes
← Back to home

Submit Feedback