Pith. sign in

REVIEW 7 cited by

PaSa: An LLM Agent for Comprehensive Academic Paper Search

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 2501.10120 v2 pith:7JXV5FMB submitted 2025-01-17 cs.IR cs.LG

classification cs.IRcs.LG
keywords pasagooglegpt-4oqueriesacademicrecallsearchagent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce PaSa, an advanced Paper Search agent powered by large language models. PaSa can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholar queries. We optimize PaSa using reinforcement learning with a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained academic queries and corresponding papers sourced from top-tier AI conference publications. Additionally, we develop RealScholarQuery, a benchmark collecting real-world academic queries to assess PaSa performance in more realistic scenarios. Despite being trained on synthetic data, PaSa significantly outperforms existing baselines on RealScholarQuery, including Google, Google Scholar, Google with GPT-4o for paraphrased queries, ChatGPT (search-enabled GPT-4o), GPT-o1, and PaSa-GPT-4o (PaSa implemented by prompting GPT-4o). Notably, PaSa-7B surpasses the best Google-based baseline, Google with GPT-4o, by 37.78% in recall@20 and 39.90% in recall@50, and exceeds PaSa-GPT-4o by 30.36% in recall and 4.25% in precision. Model, datasets, and code are available at https://github.com/bytedance/pasa.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A pre-training task called RAMP, where models practice searching to fill masked text spans, improves downstream agentic open-domain QA performance across Qwen and LLaMA models.

  2. InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation

    cs.IR 2025-05 conditional novelty 6.0 of 10

    InfoDeepSeek is a 245-question benchmark that measures how well AI agents seek information on the live web, with new metrics for answer accuracy, evidence quality, and compactness.

  3. 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.

  4. Prompt-to-Paper: Agentic AI System for Bioinformatics

    cs.AI 2026-07 conditional novelty 4.5 of 10

    An agentic bioinformatics manuscript system with deterministic RAG, real experiment execution, and a quality-driven rewrite loop raises automated scores by ~18 points on five case studies at ~$0.31 per paper.

  5. AI for Auto-Research: Roadmap & User Guide

    cs.AI 2026-05 unverdicted novelty 4.0 of 10

    The paper delivers a stage-by-stage roadmap for AI in research, showing reliable assistance in retrieval and tool tasks but fragility in novelty and judgment, advocating human-governed collaboration.

  6. AI4Research: A Survey of Artificial Intelligence for Scientific Research

    cs.CL 2025-07 conditional novelty 4.0 of 10

    A survey that organizes AI-for-research work into five tasks, comprehension, survey, discovery, writing, and peer review, and compiles associated tools and benchmarks.

  7. AI Scientists Fail Without Strong Implementation Capability

    cs.AI 2025-06 conditional novelty 4.0 of 10

    AI scientist systems can propose ideas but cannot reliably implement and verify experiments, making the implementation gap, not idea generation, the current bottleneck.

Pith tools