Pith. sign in

REVIEW 9 cited by

O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering

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

arxiv 2505.16582 v2 pith:BXRD33ND submitted 2025-05-22 cs.CL cs.AI

classification cs.CLcs.AI
keywords open-endedknowledgesearcheragentmodelquestionsanswerclosed-ended
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Large Language Models (LLMs), despite their advancements, are fundamentally limited by their static parametric knowledge, hindering performance on tasks requiring open-domain up-to-date information. While enabling LLMs to interact with external knowledge environments is a promising solution, current efforts primarily address closed-end problems. Open-ended questions, which characterized by lacking a standard answer or providing non-unique and diverse answers, remain underexplored. To bridge this gap, we present O$^2$-Searcher, a novel search agent leveraging reinforcement learning to effectively tackle both open-ended and closed-ended questions in the open domain. O$^2$-Searcher leverages an efficient, locally simulated search environment for dynamic knowledge acquisition, effectively decoupling the external world knowledge from model's sophisticated reasoning processes. It employs a unified training mechanism with meticulously designed reward functions, enabling the agent to identify problem types and adapt different answer generation strategies. Furthermore, to evaluate performance on complex open-ended tasks, we construct O$^2$-QA, a high-quality benchmark featuring 300 manually curated, multi-domain open-ended questions with associated web page caches. Extensive experiments show that O$^2$-Searcher, using only a 3B model, significantly surpasses leading LLM agents on O$^2$-QA. It also achieves SOTA results on various closed-ended QA benchmarks against similarly-sized models, while performing on par with much larger ones.

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.

  1. Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents

    cs.AI 2026-08 conditional novelty 6.0 of 10

    Fetch-then-Explore, which stores fetched pages in a per-question workspace and extracts evidence on demand with grep/read, beats visit-and-read and browsing baselines on BrowseComp across three LLM backbones.

  2. MemHarness: Memory Is Reconstructed, Not Replayed

    cs.AI 2026-07 conditional novelty 6.0 of 10

    End-to-end GRPO training teaches a unified LLM policy to reconstruct retrieved experiences into state-aligned guidance, outperforming verbatim memory replay on ALFWorld and WebShop.

  3. Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Reward

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    DecomposeR represents research plans as typed DAGs and uses two-stage planner-then-answerer RL to improve long-form research performance by 5.1-8.0 points over baselines.

  4. The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios

    cs.AI 2026-01 conditional novelty 6.0 of 10

    Trainee-Bench evaluates LLM agents on scheduling, active exploration, and continual learning in randomized workplace scenarios; the best current model completes only 35% of tasks.

  5. EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

    cs.CL 2025-10 unverdicted novelty 6.0 of 10

    EvolveR enables LLM agents to self-evolve via a closed loop of distilling interaction trajectories into strategic principles offline and retrieving them to guide online decisions with policy reinforcement, yielding be...

  6. ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning

    cs.CL 2025-08 unverdicted novelty 6.0 of 10

    ParallelSearch applies reinforcement learning with parallel-decomposition rewards to teach LLM search agents to issue independent sub-queries concurrently, lifting QA accuracy by 2.9% on average and 12.7% on paralleli...

  7. EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

    cs.CL 2025-10 unverdicted novelty 5.0 of 10

    EvolveR proposes a closed-loop self-evolution system for LLM agents that distills experiences into principles offline and applies reinforcement during online task interactions to achieve better performance on multi-ho...

  8. Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs

    cs.CL 2025-10 unverdicted novelty 5.0 of 10

    ERL trains LLMs to erase faulty reasoning steps and regenerate them in place, yielding gains of up to 8.48% EM on multi-hop QA benchmarks like HotpotQA.

  9. DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents

    cs.CV 2026-05 unverdicted novelty 4.0 of 10

    DocArena automates creation of multimodal document QA training data via MLLM-based structuring and cross-page reasoning pairs, yielding agents with top retrieval and QA performance in unified tests.

Pith tools