TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM Agents

• URL: http://arxiv.org/abs/2609.03383v1
• Date: Thu, 03 Sep 2026 05:32:43 GMT
• Title: TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM Agents
• Abstract summary: We propose emphTemporal Instance-Graph Policy Optimization (TIGPO), which extends graph-based credit assignment across policy updates.<n>TIGPO maintains a persistent transition graph for each task, allowing valid transitions discovered by different policy versions to jointly determine credit for current rollouts.<n>Experiments on ALFWorld and WebShop demonstrate that TIGPO consistently outperforms prior group-based and graph-based policy optimization methods.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph-based policy optimization improves credit assignment for long-horizon LLM agents by organizing rollout trajectories into state-transition graphs. However, existing methods construct graphs independently within each policy update, discarding transitions discovered by earlier policies and limiting advantage estimation to small, batch-local rollout groups. We propose \emph{Temporal Instance-Graph Policy Optimization} (TIGPO), which extends graph-based credit assignment across policy updates. TIGPO maintains a persistent transition graph for each task, allowing valid transitions discovered by different policy versions to jointly determine credit for current rollouts. To actively reconnect current exploration with historical experience, TIGPO allocates a fixed rollout budget between Exploration slots for ordinary task sampling and Revisit slots for delayed reattempts of previously explored tasks. For each revisit, TIGPO pairs the current rollout group with its corresponding earlier Exploration group to construct a cross-temporal reference. The enlarged reference is designed to stabilize relative advantage estimation under small rollout groups, while comparison on the same task directly captures policy improvement across training stages. Historical transitions and scores serve only as structural and detached statistical references and are never replayed in the policy loss. Experiments on ALFWorld and WebShop demonstrate that TIGPO consistently outperforms prior group-based and graph-based policy optimization methods.

Related papers

• Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks [17.832722956008656]
  Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards.<n>We propose Progress-conditioned Group Policy Optimization (ProGPO), which uses first-visit observation coverage only when all samples in a group receive zero outcome reward.<n>Experiments on two challenging agentic benchmarks, ALFWorld and WebShop with Qwen2.5-1.5/7B-Instruct, show that ProGPO consistently improves over group-based baselines.
  arXiv  Detail & Related papers  (2026-07-22T04:01:56Z)
• RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts [84.20747697259326]
  Group Relative Policy Optimization (GRPO) has shown strong effectiveness in reinforcement learning from verifiable feedback.<n>We propose textbfReference-Relative Policy Optimization (RRPO), which generalizes GRPO by replacing direct correctness-based advantage construction with reference-relative contrastive comparisons.<n>We evaluate RRPO using anchor-based contrastive advantages throughout policy optimization, without relying on task ground-truth verifiers.
  arXiv  Detail & Related papers  (2026-07-20T19:40:25Z)
• Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning [5.952158244195666]
  We propose ProGPO, a learned-critic-free method for context-consistent step-level learning.<n>We evaluate ProGPO on two challenging agentic tasks, ALFWorld and WebShop, with Qwen2.5-1.5B-Instruct.
  arXiv  Detail & Related papers  (2026-07-05T11:41:46Z)
• Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning [85.02566758103008]
  Group-Graph Policy Optimization (G2PO) is a novel group-based Reinforcement Learning algorithm tailored for multi-turn agentic tasks.<n>G2PO substantially outperforms state-of-the-art prompt-based and RL baselines, achieving remarkable success rate improvements of up to 22.2% over GRPO.
  arXiv  Detail & Related papers  (2026-06-22T08:12:47Z)
• ReFPO: Reflow Regularization for Flow Matching Policy Gradients [58.32178725687043]
  We present a simple online RL method that adds explicit Reflow regularization to Flow Matching Policy Gradients.<n>We experimentally demonstrate that ReFPO improves average performance and discretization across GridWorld, MuJoCo Playground, and high-dimensional Humanoid Control tasks.
  arXiv  Detail & Related papers  (2026-06-19T04:23:10Z)
• TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models [49.463896453707065]
  Vision-Language-Action (VLA) models have made remarkable progress, but they remain vulnerable to distribution shifts at deployment time.<n>Recent VLA models suggest that prompts can serve as an efficient interface for steering policy behavior, but existing prompt-based steering typically relies on external guidance.<n>This raises a natural question: can test-time training (TTT) for VLA be achieved by optimizing a prompt, so that the steering interface itself can be learned and adapted from interaction?<n>We address this question with TTT-VLA, a test-time training framework based on Latent Prompt Optimization (LPO)
  arXiv  Detail & Related papers  (2026-06-02T04:10:39Z)
• One-Way Policy Optimization for Self-Evolving LLMs [63.8638342097375]
  Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs)<n>We propose One-Way Policy Optimization (OWPO), a method based on the principle of decoupling optimization direction from update magnitude.<n> Experimental results demonstrate that OWPO outperforms strong baselines, including DAPO, OPD, and MOPD.
  arXiv  Detail & Related papers  (2026-05-21T08:25:27Z)
• OGPO: Sample Efficient Full-Finetuning of Generative Control Policies [53.42266064673132]
  Generative control policies (GCPs) have emerged as effective parameterizations for robot learning.<n>This work introduces Off-policy Generative Policy Optimization (OGPO), a sample-efficient for finetuning GCPs.<n>OGPO achieves state-of-the-art performance on manipulation tasks spanning multi-task settings, high-precision insertion, and dexterous control.
  arXiv  Detail & Related papers  (2026-05-04T18:36:40Z)
• Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks [23.119173310662365]
  Group-based reinforcement learning (RL) has advanced the capabilities of large language models on long-horizon agentic tasks.<n>We find a key issue in estimating stepwise relative advantages, namely context inconsistency, where steps within the same group may differ in their historical contexts.<n>We propose HGPO, which assigns each step to multiple hierarchical groups according to the consistency of historical contexts.
  arXiv  Detail & Related papers  (2026-02-26T09:58:10Z)
• On the Theory and Practice of GRPO: A Trajectory-Corrected Approach with Fast Convergence [2.8165669455824696]
  Group Relative Policy Optimization is a critic-free reinforcement learning algorithm.<n>We show that GRPO update rule estimates the policy gradient at the old policy rather than the current one.<n>We propose a new algorithm: Trajectory level Importance Corrected GRPO.
  arXiv  Detail & Related papers  (2025-08-04T19:01:19Z)

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.