Pith. sign in

REVIEW 14 cited by

Dr. Zero: Self-Evolving Search Agents without Training Data

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 2601.07055 v2 pith:NBYZLVZC submitted 2026-01-11 cs.AI

Dr. Zero: Self-Evolving Search Agents without Training Data

classification cs.AI
keywords searchagentstrainingdatawithoutproposerreasoningself-evolution
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

As high-quality data becomes increasingly difficult to obtain, self-evolution without curated training data has emerged as a promising paradigm. This approach allows large language models (LLMs) to autonomously generate and solve complex problems, thereby improving their reasoning capabilities. However, multi-turn search agents struggle in this setting due to limited question diversity and the substantial compute required for multi-step reasoning and tool use. In this work, we introduce Dr. Zero, a framework that enables search agents to effectively self-evolve without human-annotated training data, relying solely on an external search engine as their knowledge environment. In particular, we design a self-evolution feedback loop where a proposer generates structurally diverse questions to train a solver initialized from the same base model. As the solver evolves, it incentivizes the proposer to produce increasingly difficult yet solvable tasks, thus establishing an automated curriculum to refine both agents. To enhance training efficiency, we also introduce hop-grouped relative policy optimization (HRPO). This method clusters structurally similar questions to construct group-level baselines, effectively minimizing the sampling overhead in evaluating each query's individual difficulty and solvability. Consequently, HRPO significantly reduces the compute requirements for proposer training and reward estimation without compromising performance or stability. Extensive experimental results demonstrate that Dr. Zero matches or surpasses fully supervised search agents on several question answering benchmarks, showing that strong agentic search and evidence-grounded reasoning can emerge solely through self-evolution.

discussion (0)

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

Forward citations

Cited by 14 Pith papers

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

  1. Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning

    cs.CV 2026-06 unverdicted novelty 7.0

    A closed-loop self-evolving training system for spatial reasoning in MLLMs that iteratively generates QA pairs matched to the model's current capabilities via confidence feedback, achieving gains with an order of magn...

  2. EXG: Self-Evolving Agents with Experience Graphs

    cs.AI 2026-05 unverdicted novelty 7.0

    EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.

  3. EvoGround: Self-Evolving Video Agents for Video Temporal Grounding

    cs.CV 2026-05 unverdicted novelty 7.0

    A proposer-solver agent pair achieves supervised-level video temporal grounding and fine-grained captioning from 2.5K unlabeled videos via self-reinforcing evolution.

  4. $\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data

    cs.LG 2026-04 conditional novelty 7.0

    Self-play’s natural question-construction paths supply free privileged information that turns sparse-reward self-play into dense self-distillation, yielding stronger data-free search agents.

  5. Retrieval Augmented Conversational Recommendation with Reinforcement Learning

    cs.IR 2026-04 unverdicted novelty 7.0

    RAR retrieves candidate items from a 300k-movie corpus then uses LLM generation with RL feedback to produce context-aware recommendations that outperform baselines on benchmarks.

  6. Self-Evolving Deep Research via Joint Generation and Evaluation

    cs.CL 2026-06 unverdicted novelty 6.0

    SCORE is a shared-parameter co-evolutionary framework coupling generation and evaluation of deep research reports with a meta-harness to adapt evaluation standards as performance improves.

  7. EVE-Agent: Evidence-Verifiable Self-Evolving Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    EVE-Agent adds an evidence verifier to the proposer-solver loop that rewards spans by marginal accuracy gain, producing self-generated but inspectable training examples for search agents.

  8. Towards Direct Evaluation of Harness Optimizers via Priority Ranking

    cs.AI 2026-05 unverdicted novelty 6.0

    Priority ranking offers a low-cost direct evaluation for harness optimizers that correlates with their real multi-step optimization performance, supported by the Shor dataset of 182 scenarios.

  9. RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data

    cs.RO 2026-05 unverdicted novelty 6.0

    A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.

  10. PREPING: Building Agent Memory without Tasks

    cs.AI 2026-05 unverdicted novelty 6.0

    Preping builds agent memory via proposer-guided synthetic practice and selective validation, matching offline/online methods at 2-3x lower deployment cost.

  11. Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration

    cs.AI 2026-04 unverdicted novelty 6.0

    LLM agents trained with a task-success reward on self-generated knowledge can spontaneously explore and adapt to new environments without any rewards or instructions at inference, yielding 20% gains on web tasks and a...

  12. $\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data

    cs.LG 2026-04 unverdicted novelty 6.0

    π-Play uses self-generated question construction paths as privileged information in multi-agent self-distillation to convert sparse-reward self-play into a dense-feedback loop, surpassing supervised search agents and ...

  13. Self-Evolving World Models for LLM Agent Planning

    cs.AI 2026-06 unverdicted novelty 5.0

    WorldEvolver uses episodic memory, semantic memory, and selective foresight to self-evolve world models at test time, achieving top prediction accuracy and agent success on ALFWorld and ScienceWorld benchmarks.

  14. SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution

    cs.CL 2026-06 unverdicted novelty 5.0

    SEVA trains a verification agent with a decomposed process reward to produce structured fact attributions, enabling a self-evolution loop that matches GPT-4o-mini F1 on ClearFacts while generating richer output.