pith. sign in

arxiv: 2502.04644 · v2 · pith:EGEHBSVGnew · submitted 2025-02-07 · 💻 cs.AI · cs.CL

Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools

classification 💻 cs.AI cs.CL
keywords reasoningagenticframeworkagentagentscodedeepenhancing
0
0 comments X
read the original abstract

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address complex problems requiring deep research. A key innovation in our framework is the Mind-Map agent, which constructs a structured knowledge graph to store reasoning context and track logical relationships, ensuring coherence in long reasoning chains with extensive tool usage. Additionally, we conduct a comprehensive exploration of the Web-Search agent, leading to a highly effective search mechanism that surpasses all prior approaches. When deployed on DeepSeek-R1, our method achieves a new state-of-the-art (SOTA) among public models and delivers performance comparable to OpenAI Deep Research, the leading proprietary model in this domain. Extensive ablation studies validate the optimal selection of agentic tools and confirm the effectiveness of our Mind-Map and Web-Search agents in enhancing LLM reasoning. The code is at: https://github.com/theworldofagents/Agentic-Reasoning

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

    cs.CL 2026-06 unverdicted novelty 7.0

    FORT synthesizes shortcut-resistant search tasks by controlling four identified shortcut risks across entity selection, graph construction, question formulation, and refinement, producing training data that yields age...

  2. IE as Cache: Information Extraction Enhanced Agentic Reasoning

    cs.CL 2026-04 unverdicted novelty 7.0

    IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.

  3. Efficient Remote KV Cache Reuse with GPU-native Video Codec

    cs.DC 2026-02 conditional novelty 7.0

    KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.

  4. When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering

    cs.CL 2026-01 conditional novelty 7.0

    Iterative RAG outperforms Gold Context RAG by up to 25.6 points on ChemKGMultiHopQA across 11 LLMs, mainly by staging retrieval to avoid context overload and correct hypothesis drift.

  5. Code Researcher: Deep Research Agent for Large Systems Code and Commit History

    cs.SE 2025-05 unverdicted novelty 7.0

    Code Researcher retrieves global context via multi-step reasoning on code semantics, patterns, and commit history to fix Linux kernel crashes, reaching 48% crash-resolution rate versus 31% for baselines.

  6. Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

    cs.CL 2026-05 unverdicted novelty 6.0

    AXPO addresses the Thinking-Acting Gap in agentic RL training by targeted resampling of tool calls in all-wrong subgroups, delivering +1.8pp gains over GRPO on nine multimodal benchmarks with an 8B model beating a 32B...

  7. Towards Knowledgeable Deep Research: Framework and Benchmark

    cs.AI 2026-04 unverdicted novelty 6.0

    The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.

  8. MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue

    cs.CL 2026-03 unverdicted novelty 6.0

    MICA combines incremental per-turn distance rewards and Monte Carlo returns from a shared potential function over user support states to create a mixed advantage signal that enables stable multi-turn RL optimization f...

  9. Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports

    cs.SE 2026-05 unverdicted novelty 5.0

    RAG reaches 0.66 weighted F1 on invalid bug report subclassification while agentic web search reaches 68.9% judge success on no-code fix generation, using a new gold-standard benchmark.

  10. The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

    cs.CL 2026-06 unverdicted novelty 4.0

    A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.

  11. EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools

    cs.AI 2026-04 unverdicted novelty 4.0

    Structured query and evidence tools added to an AI research agent improve benchmark accuracy by 0.6 to 3.8 percentage points.

  12. Agentic Reasoning for Large Language Models

    cs.AI 2026-01 unverdicted novelty 4.0

    The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applicat...

  13. Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary

    cs.AI 2025-06 unverdicted novelty 4.0

    Agents should invoke external tools only when epistemically necessary, per the introduced Theory of Agent framework that frames tool use as a decision under uncertainty.

  14. From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review

    cs.AI 2025-04 accept novelty 4.0

    A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.

  15. Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports

    cs.SE 2026-05 unverdicted novelty 3.0

    Retrieval-augmented generation reaches 0.66 weighted F1 for invalid bug report subclassification while agentic web search reaches 68.9% Judge LLM success for no-code fix generation.