WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning

• URL: http://arxiv.org/abs/2601.03164v2
• Date: Wed, 07 Jan 2026 02:00:39 GMT
• Title: WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning
• Authors: Xinmiao Yu, Liwen Zhang, Xiaocheng Feng, Yong Jiang, Bing Qin, Pengjun Xie, Jingren Zhou,
• Abstract summary: Large Language Model(LLM)-based agents have shown strong capabilities in web information seeking.<n>Plan anchor is where the first reasoning step disproportionately impacts downstream behavior in long-horizon web reasoning tasks.<n>We propose Anchor-GRPO, a two-stage RL framework that decouples planning and execution.
• Score: 82.12501258760814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Model(LLM)-based agents have shown strong capabilities in web information seeking, with reinforcement learning (RL) becoming a key optimization paradigm. However, planning remains a bottleneck, as existing methods struggle with long-horizon strategies. Our analysis reveals a critical phenomenon, plan anchor, where the first reasoning step disproportionately impacts downstream behavior in long-horizon web reasoning tasks. Current RL algorithms, fail to account for this by uniformly distributing rewards across the trajectory. To address this, we propose Anchor-GRPO, a two-stage RL framework that decouples planning and execution. In Stage 1, the agent optimizes its first-step planning using fine-grained rubrics derived from self-play experiences and human calibration. In Stage 2, execution is aligned with the initial plan through sparse rewards, ensuring stable and efficient tool usage. We evaluate Anchor-GRPO on four benchmarks: BrowseComp, BrowseComp-Zh, GAIA, and XBench-DeepSearch. Across models from 3B to 30B, Anchor-GRPO outperforms baseline GRPO and First-step GRPO, improving task success and tool efficiency. Notably, WebAnchor-30B achieves 46.0% pass@1 on BrowseComp and 76.4% on GAIA. Anchor-GRPO also demonstrates strong scalability, getting higher accuracy as model size and context length increase.

Related papers

• iGRPO: Self-Feedback-Driven LLM Reasoning [88.83313431248473]
  Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions.<n>We introduce Iterative Group Relative Policy Optimization (iGRPO), a two-stage extension of GRPO that adds dynamic self-conditioning through model-generated drafts.<n>Under matched rollout budgets, iGRPO consistently outperforms GRPO across base models.
  arXiv  Detail & Related papers  (2026-02-09T18:45:11Z)
• TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization [97.18886232580131]
  Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration.<n>We propose Turn-Level GRPO, a lightweight RL algorithm that performs turn-level group sampling for fine-grained optimization.
  arXiv  Detail & Related papers  (2026-01-23T06:21:33Z)
• TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models [14.130608036489336]
  Reinforcement learning (RL) post-training is crucial for aligning generative models with human preferences, but its prohibitive computational cost remains a major barrier to widespread adoption.<n>We introduce textbfTreeGRPO, a novel RL framework that dramatically improves training efficiency by recasting the denoising process as a search tree.
  arXiv  Detail & Related papers  (2025-12-09T01:17:34Z)
• Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization [13.475938754147625]
  Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks.<n>Agentic Reinforcement Learning (Agentic RL) optimize such models over full tool-interaction trajectories.<n>Two key challenges hinder effectiveness: (1) Sparse, non-instructive rewards, such as binary 0-1 verifiable signals, provide limited guidance for intermediate steps and slow convergence.<n>We propose two complementary techniques: Progressive Reward Shaping (PRS) and Value-based Sampling Policy Optimization (VSPO).
  arXiv  Detail & Related papers  (2025-12-08T11:59:25Z)
• Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control [72.43808515668947]
  We introduce Hi-Agent, a trainable hierarchical vision-language agent for mobile control.<n>Hi-Agent features a high-level reasoning model and a low-level action model that are jointly optimized.<n>Hi-Agent achieves a new State-Of-The-Art (SOTA) 87.9% task success rate on the Android-in-the-Wild (AitW) benchmark.
  arXiv  Detail & Related papers  (2025-10-16T07:38:21Z)
• In-the-Flow Agentic System Optimization for Effective Planning and Tool Use [73.72524040856052]
  AgentFlow is a trainable, in-the-flow agentic framework that coordinates four modules (planner, executor, verifier, generator) through an evolving memory.<n>Flow-GRPO tackles long-horizon, sparse-reward credit assignment by converting multi-turn optimization into a sequence of tractable single-turn policy updates.<n>AgentFlow with a 7B-scale backbone outperforms top-performing baselines with average accuracy gains of 14.9% on search, 14.0% on agentic, 14.5% on mathematical, and 4.1% on scientific tasks.
  arXiv  Detail & Related papers  (2025-10-07T05:32:44Z)
• TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization [12.061547251822326]
  Trajectory-based Group Relative Policy Optimization (TGRPO) is an online RL-based training framework for Visual-Language-Action (VLA) models.<n>We show that TGRPO achieves an average success rate of 80.7%, which is 4.2% higher than that of Supervised Fine-Tuning (SFT) and outperforms other representative RL-based post-training methods.
  arXiv  Detail & Related papers  (2025-06-10T04:27:49Z)
• Group-in-Group Policy Optimization for LLM Agent Training [17.243181792126563]
  Group-in-Group Policy Optimization (GiGPO) is a novel RL algorithm that achieves fine-grained credit assignment for LLM agents.<n>We evaluate GiGPO on challenging agent benchmarks, including ALFWorld and WebShop, as well as tool-integrated reasoning on search-augmented QA tasks.
  arXiv  Detail & Related papers  (2025-05-16T08:26:59Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development.<n>We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents.<n>We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control [1.1404490220482764]
  BRO is a model-free algorithm to achieve near-optimal policies in the Dog and Humanoid tasks.<n>BRO achieves state-of-the-art results, significantly outperforming the leading model-based and model-free algorithms.<n>BRO is the first model-free algorithm to achieve near-optimal policies in the notoriously challenging Dog and Humanoid tasks.
  arXiv  Detail & Related papers  (2024-05-25T09:53:25Z)
• Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration [87.53543137162488]
  We propose an easy-to-implement online reinforcement learning (online RL) framework called textttMEX. textttMEX integrates estimation and planning components while balancing exploration exploitation automatically. It can outperform baselines by a stable margin in various MuJoCo environments with sparse rewards.
  arXiv  Detail & Related papers  (2023-05-29T17:25:26Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.