agentic-reasoning

Tag

Cards List
#agentic-reasoning

@KirkDBorne: New survey report >> Agentic Reasoning for Large Language Models: https://arxiv.org/abs/2601.12538 [135-page PDF]

X AI KOLs Timeline ↗ · 2026-11-01 Cached

A 135-page survey paper organizing agentic reasoning for large language models along three layers—foundational, self-evolving, and collective multi-agent reasoning—spanning in-context and post-training optimization with real-world applications and open challenges.

0 favorites 0 likes
#agentic-reasoning

DocSkill: Skill-Integrated Agentic Reasoning for Multilingual Multi-Hop Document Question Answering

arXiv cs.CL ↗ · 2026-10-28 Cached

DocSkill提出一种带技能编排策略的智能体框架,用于多语言多跳文档问答,通过MCTS离线探索轨迹并结合SFT/DPO训练策略,同时发布包含60K QA对、覆盖10种语言的MMHop-DocBench数据集。

0 favorites 0 likes
#agentic-reasoning

MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports

arXiv cs.AI ↗ · 2026-10-26

The paper introduces MedCaseAgent, an agentic framework that turns unstructured clinical notes into publication-quality rare disease case reports by combining hierarchical patient data mining with iterative tool-integrated reasoning. It also releases the MedCase-150K corpus, MedCase-Bench evaluation suite, and an open-source model post-trained from Qwen3.5-9B that outperforms existing medical LLMs and agents.

0 favorites 0 likes
#agentic-reasoning

LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management

arXiv cs.AI ↗ · 2026-10-12 Cached

LongHarness 是一个模型无关的智能体框架,通过「证据-结论协同演化」和「证据生命周期管理」机制,在超过 1 亿 token 的文档语料上进行有状态的证据管理,显著提升了长上下文推理任务的准确率(如 OfficeQA Pro V1 上从 15.8% 提升至 60.2%),并超越了 Claude Code 和 Codex 等现有智能体框架。

0 favorites 0 likes
#agentic-reasoning

@omarsar0: Great paper from Meta Superintelligence Labs on compounding inference for long-horizon agents. One clear approach that'…

X AI KOLs Timeline ↗ · 2026-10-11 Cached

Meta Superintelligence Labs的研究者提出GitSwarm,一个通过共享Git仓库进行结构化持久记忆的异步多智能体系统,实现"compounding inference",使中间成果可被后续计算继承、扩展与组合;在IMOProofBench-Advanced上一次运行解出全部30题,在ProgramBench上取得79.4%的成绩。

0 favorites 0 likes
#agentic-reasoning

@NousResearch: Wild MISSINGNO. appeared! A coding and agentic reasoning model that is highly token efficient, free for a limited time …

X AI KOLs Timeline ↗ · 2026-10-10 Cached

Nous Research 发布了名为 MISSINGNO. 的编码与智能体推理模型,主打高 token 效率,并在 Nous Portal 上限时免费提供,可直接在 Hermes Agent 中使用。

0 favorites 0 likes
#agentic-reasoning

@dair_ai: Super interesting paper from Meta Superintelligence Labs on controlling long agent runs. They use the same workers and …

X AI KOLs Timeline ↗ · 2026-10-02 Cached

Meta Superintelligence Labs introduces agentic meta-reasoning, an inference-time harness where a controller decides what work to run next in long agent runs, boosting ProgramBench from 63.7% to 71.5% with GPT-5.5 under the same workers and budget. Gains of 3.6-4.2 points hold across ProofBench, ARC-AGI-2 and LongCoT-mini when averaged over frontier models.

0 favorites 0 likes
#agentic-reasoning

@omarsar0: Interesting paper on agent memory stored as a linked markdown wiki. Lots of great ideas and insights if you work with L…

X AI KOLs Timeline ↗ · 2026-09-23 Cached

The paper proposes Wiki Foundation Model (WFM), a novel foundation model for scalable, agent-native representation and retrieval using LLM Wiki, which couples dense text with link structure, achieving strong performance on benchmarks and 10.5x training acceleration.

0 favorites 0 likes
#agentic-reasoning

WFM: Wiki Foundation Model for Complex Agentic Reasoning

arXiv cs.AI ↗ · 2026-09-17 Cached

The paper proposes WFM, a Wiki Foundation Model for scalable, agent-native knowledge representation and retrieval, demonstrating improved performance in complex agentic reasoning tasks with a 10.5x training acceleration.

0 favorites 0 likes
#agentic-reasoning

Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation

arXiv cs.AI ↗ · 2026-09-12 Cached

ARCHE is an autonomous agentic system that integrates reasoning and computational models to automate the discovery and validation of chemical reaction mechanisms, validated through various chemical scenarios.

0 favorites 0 likes
#agentic-reasoning

Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning

Hugging Face Daily Papers ↗ · 2026-08-27 Cached

This paper introduces an agentic framework combining LLMs and VLMs for consistent multi-instruction video editing across multiple shots, and proposes the MMLVE task and benchmark to evaluate performance.

0 favorites 0 likes
#agentic-reasoning

DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation

arXiv cs.AI ↗ · 2026-08-19 Cached

DeAR is a decentralized agentic reasoning framework that enhances accuracy in knowledge-intensive reasoning tasks through capability grounding and collaborative thought navigation, outperforming centralized methods on multimodal benchmarks.

0 favorites 0 likes
#agentic-reasoning

Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning

arXiv cs.AI ↗ · 2026-08-13 Cached

This paper presents a unified global-to-local paradigm for video anomaly detection, introducing a training-free framework (GtS) and a tool-augmented agentic reasoning method with reinforcement learning, along with a new benchmark VAGU-T and metric JeAUG.

0 favorites 0 likes
#agentic-reasoning

QuantumMind: Constraint-Grounded Agentic Reasoning for Speedup Analysis in Quantum Computing

arXiv cs.AI ↗ · 2026-08-11 Cached

QuantumMind presents an auditable agentic workflow that automatically generates and screens quantum speedup hypotheses using typed role-specialized actions and a deterministic validator.

0 favorites 0 likes
#agentic-reasoning

@maximelabonne: It didn't take two days to get the first fine-tunes of LFM2.5-2.6B. This one looks cool!

X AI KOLs Following ↗ · 2026-08-06 Cached

Maxime Labonne highlights early fine-tunes of LFM2.5-2.6B, while Bad Theory Labs releases two open-weight models: BTL-4 35B, a frontier agentic reasoning model, and Macaw 2.7B, an on-device Mac agent, with notable BFCL v4 performance.

0 favorites 0 likes
#agentic-reasoning

CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting

arXiv cs.AI ↗ · 2026-08-05 Cached

CastFSR is a Fast–Slow–Reflect agentic reasoning framework that leverages LLMs for context-aware time series forecasting, combining fast lightweight forecasters, slow deliberative reasoning, and reflective evaluation to improve forecasting accuracy and consistency.

0 favorites 0 likes
#agentic-reasoning

Agentic Graph Token Reasoning

arXiv cs.LG ↗ · 2026-08-04 Cached

Introduces agentic graph token reasoning, a method that recasts graph tokenization as part of an LLM's step-by-step reasoning process, allowing the model to dynamically choose graph views and granularity during inference. The method outperforms baselines across seven graph domains and transfers zero-shot to unseen domains.

0 favorites 0 likes
#agentic-reasoning

LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger

Hugging Face Daily Papers ↗ · 2026-07-30 Cached

This paper introduces LedgerMind, a provenance-constrained multimodal agentic reasoning framework that uses a Structured Evidence Ledger to ensure grounded, faithful reasoning in visual question answering, addressing failure patterns like hallucination and over-reasoning.

0 favorites 0 likes
#agentic-reasoning

SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs

arXiv cs.AI ↗ · 2026-07-28 Cached

SCAIR introduces a training-free framework for reasoning over enterprise knowledge graphs by injecting schema-conditioned structural priors and enforcing schema-aware traversal during multi-hop reasoning, showing improvements on a real-world CMDB benchmark.

0 favorites 0 likes
#agentic-reasoning

The Legora Benchmark for Agentic Reasoning (4 minute read)

TLDR AI ↗ · 2026-07-27 Cached

Legora introduces the Legora BAR benchmark for evaluating AI agentic reasoning in legal workflows, using real cases and the Legora harness to measure system-level performance.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback