REVIEW 21 cited by
Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
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
Forward citations
Cited by 21 Pith papers
-
When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
On ChemKGMultiHopQA, iterative retrieval-reasoning outperformed oracle gold-context static RAG for all 11 LLMs tested, with gains up to 25.6 percentage points.
-
Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks
A compact, diverse, web-scale datastore plus simple dense retrieval improves performance on MMLU, MMLU Pro, AGI Eval, GPQA, and MATH across multiple LLM families.
-
MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue
MICA mixes per-turn and whole-trajectory normalized reward signals to train emotional-support chatbots, outperforming GRPO and REINFORCE++ on EMPA, EQ-Bench, and EmoBench.
-
ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation
An LLM agent that can call a reconfiguration tool to update its sub-goals, toolbox, strategy, and context outperforms static-config agents across FRAMES, xbench, GAIA, and SWE-bench Lite.
-
LocalSearchBench: Benchmarking Agentic Search in Real-World Local Life Services
LocalSearchBench—1.3M merchant records and 900 multi-hop local-life QA tasks across 9 Chinese cities—shows the best reasoning agent reaches only 35.6% correctness.
-
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
An audit framework and empirical study showing that generative search engines and deep research agents frequently produce one-sided answers and weakly supported citations, with citation accuracy between 40 and 80%.
-
MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning
The paper advertises a self-evolving tool-using agent that beats baselines, but the body contains a different math paper, leaving the performance claims unsupported.
-
What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction
LLMs used for meta-analysis data extraction show high precision but low recall, with domain-specific prompts providing the largest recall gains and supporting a three-tier human-oversight framework.
-
SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control
SmartThinker shortens AI reasoning chains by estimating the importance of each step and penalizing the unimportant ones, preserving accuracy while using far fewer tokens.
-
Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification
A pair of reinforcement-learning-trained agents, one for reasoning and one for search, improves accuracy on multi-hop claim verification benchmarks.
-
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Tool-Star combines cold-start supervised fine-tuning with a multi-tool self-critic reinforcement learning algorithm and hierarchical rewards to improve LLM tool-use reasoning.
-
SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task
SearchArt post-trains Qwen3.5-27B on verification-filtered synthetic search trajectories, scoring 74.39 on BrowseComp-ZH, 70.06 on BrowseComp, and 52.55 on DeepResearch-Bench, competitive with several 200B-700B agents.
-
ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference
ResearchPulse extracts motivation-method chains and experimental trends from related papers, rendering them as mind maps and line charts, and releases a 100-cluster benchmark; the reported '7B beats GPT-4o' result is ...
-
Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
A survey that groups graph-empowered AI agent research into planning, execution, memory, and multi-agent coordination, plus agents-for-graphs and applications.
-
KnowCoder-V2: Deep Knowledge Analysis
KnowCoder-V2 augments deep research with offline knowledge organization and code-based knowledge computation, reporting gains on information extraction, KBQA, and LLM-judged report generation.
-
OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
A hierarchical multi-agent framework with a domain-agnostic planner trained by SFT and DPO achieves 69.70% on GAIA and lifts a Qwen2.5-32B planner by 16.37 points.
-
Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
Alita achieves 75.15% pass@1 on GAIA validation by dynamically generating and reusing MCP-based tools, but the evaluation confounds model choice with the self-evolution mechanism.
-
Deep Research Agents: A Systematic Examination And Roadmap
A survey that organizes LLM-powered deep research agents into static versus dynamic workflows and single versus multi agent architectures, and reviews their benchmarks and open challenges.
-
MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibility
MedOrch is a modular framework in which LLMs call medical tools to answer clinical questions; its headline results on Alzheimer's, chest X-ray, and VQA benchmarks are weakened by best-of-five scoring.
-
Infinite Video Understanding
The paper argues that video understanding research should aim at processing streams of arbitrary, unbounded duration and outlines the challenges, directions, and metrics needed.
-
From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications
This paper is a broad tutorial on applying LAMs and agentic AI to 6G, largely restating existing research rather than introducing new results.
Discussion (0). Sign in to comment.