Pith. sign in

REVIEW 9 cited by

Open Deep Search: Democratizing Search with Open-source Reasoning Agents

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2503.20201 v1 pith:7UBGFIG3 submitted 2025-03-26 cs.LG cs.CLcs.IR

Salaheddin Alzubi , Creston Brooks , Purva Chiniya , Edoardo Contente , Chiara von Gerlach , Lucas Irwin , Yihan Jiang , Arda Kaz
show 4 more authors
Windsor Nguyen Sewoong Oh Himanshu Tyagi Pramod Viswanath
This is my paper
classification cs.LGcs.CLcs.IR
keywords searchreasoningopenframesopen-sourcetoolllmssimpleqa
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce Open Deep Search (ODS) to close the increasing gap between the proprietary search AI solutions, such as Perplexity's Sonar Reasoning Pro and OpenAI's GPT-4o Search Preview, and their open-source counterparts. The main innovation introduced in ODS is to augment the reasoning capabilities of the latest open-source LLMs with reasoning agents that can judiciously use web search tools to answer queries. Concretely, ODS consists of two components that work with a base LLM chosen by the user: Open Search Tool and Open Reasoning Agent. Open Reasoning Agent interprets the given task and completes it by orchestrating a sequence of actions that includes calling tools, one of which is the Open Search Tool. Open Search Tool is a novel web search tool that outperforms proprietary counterparts. Together with powerful open-source reasoning LLMs, such as DeepSeek-R1, ODS nearly matches and sometimes surpasses the existing state-of-the-art baselines on two benchmarks: SimpleQA and FRAMES. For example, on the FRAMES evaluation benchmark, ODS improves the best existing baseline of the recently released GPT-4o Search Preview by 9.7% in accuracy. ODS is a general framework for seamlessly augmenting any LLMs -- for example, DeepSeek-R1 that achieves 82.4% on SimpleQA and 30.1% on FRAMES -- with search and reasoning capabilities to achieve state-of-the-art performance: 88.3% on SimpleQA and 75.3% on FRAMES.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. SciDataSailor: Deep Scientific Data Exploring

    cs.AI 2026-07 conditional novelty 6.0 of 10

    SciDataSailor uses Monte Carlo tree search to synthesize tool-use trajectories for training and benchmarking LLM agents that explore raw scientific repositories.

  2. Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Rewarding each parallel reasoning path by Monte-Carlo-Shapley marginal contribution, scored by a generative reward model, lifts Pass@16 on AIME24/AIME25/AMC23 by 4-90% relative over Parallel-R1 with a fifth of the tra...

  3. SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents

    cs.AI 2025-09 conditional novelty 6.0 of 10

    A 20B autonomously reasoning deep-research agent trained with synthetic-data RL reaches 28.7% on Humanity's Last Exam, exceeding several larger and proprietary baselines.

  4. One Interaction Is Worth a Thousand Guesses: Benchmarking the Interactive Capabilities of Deep Research Agents

    cs.CL 2026-01 conditional novelty 5.0 of 10

    IDRBench provides a reusable benchmark showing that interactive clarification improves deep-research report quality across seven LLMs, while revealing large differences in interaction efficiency.

  5. Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

    cs.LG 2025-09 conditional novelty 5.0 of 10

    EMPG re-weights policy-gradient updates by step-level token entropy, amplifying confident correct actions and muting uncertain ones, and adds a future-clarity bonus.

  6. Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    A new RL framework that rewards fine-grained reasoning steps, called Atomic Thoughts, claims better agentic deep research on seven benchmarks.

  7. Deep Researcher with Test-Time Diffusion

    cs.CL 2025-07 conditional novelty 5.0 of 10

    A test-time 'denoising' loop that repeatedly revises a draft report using fresh web retrieval, plus a component-wise self-evolution step, beats existing deep research agents on several benchmarks.

  8. KnowCoder-V2: Deep Knowledge Analysis

    cs.AI 2025-06 conditional novelty 5.0 of 10

    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.

  9. A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications

    cs.AI 2025-06 conditional novelty 4.0 of 10

    A survey of 80+ Deep Research systems that proposes a four-layer taxonomy (foundation models, tool use, planning, synthesis) and compares commercial and open-source implementations.

Pith tools