Contrastive Branch Policy Optimization

• URL: http://arxiv.org/abs/2608.24300v1
• Date: Tue, 25 Aug 2026 09:25:55 GMT
• Title: Contrastive Branch Policy Optimization
• Abstract summary: Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn interaction with external tools.<n>Existing methods tend to conflate two distinct problems: allocating a fixed rollout budget and translating branch outcomes into token-level credit.<n>We introduce Contrastive Branch Policy Optimization (CBPO), which disentangles these two problems and assigns a dedicated mechanism to each.
• Score: 16.16893757028268
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn interaction with external tools, yet its sparse outcome rewards provide no signal for identifying which intermediate decisions are responsible for success. Branch sampling induces local comparisons among alternative continuations, but existing methods tend to conflate two distinct problems: allocating a fixed rollout budget and translating branch outcomes into token-level credit. We introduce Contrastive Branch Policy Optimization (CBPO), which disentangles these two problems and assigns a dedicated mechanism to each. Generation entropy screens candidate branch positions across the entire response, while path-level and node-level decay distribute a fixed budget across trajectories and positions to prevent exploration from collapsing onto a few paths or adjacent tokens. A parent trajectory together with the branches that share an identical token prefix forms an exact-prefix group, and the reward variation within this controlled group defines the Contrastive Branch Value (CBV), an outcome-based estimate of local decision sensitivity that rescales continuation advantages without altering their sign. When multiple nodes are selected along the same trajectory, CBPO partitions it into non-overlapping credit segments, thereby avoiding duplicated gradients on shared tokens. Requiring only outcome rewards and no process-level annotation, CBPO provides a practical solution for fine-grained credit assignment in tool-integrated agent training. Extensive experiments on ten benchmarks, including five for mathematical reasoning and five for knowledge-intensive search, show that CBPO consistently outperforms state-of-the-art policy-optimization and branch-based methods, attaining the highest macro-average accuracy in both domains and across two model scales.

Related papers

• APPO: Agentic Procedural Policy Optimization [28.730334202611257]
  We study agentic RL from two perspectives: textitwhere to branch and how to assign credit after branching<n>We propose APPO, which shifts branching and credit assignment from coarse interaction units to fine-grained decision points in the sequence.<n>APPO consistently improves strong agentic RL baselines by nearly 4 points, while keeping efficient tool-calls and maintaining behavior interpretability.
  arXiv  Detail & Related papers  (2026-06-10T17:47:07Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization [55.14402862283128]
  We introduce N-GRPO, a novel exploration strategy integrated into the Group Relative Policy Optimization framework.<n>Rather than relying on token-level sampling or native embedding-level noise, our approach leverages Semantic Neighbor Mixing.<n>N-GRPO achieves consistent improvements over strong baselines on math reasoning benchmarks and also exhibits robust generalization capabilities on out-of-distribution tasks.
  arXiv  Detail & Related papers  (2026-06-09T12:21:27Z)
• Reducing Credit Assignment Variance via Counterfactual Reasoning Paths [11.514388061694268]
  Reinforcement learning for multi-step reasoning with large language models (LLMs) often relies on sparse terminal rewards.<n>We introduce a counterfactual comparison-based credit assignment framework, which samples multiple reasoning trajectories under the same input.<n>We construct an implicit process-level advantage estimator that transforms sparse terminal rewards into step-sensitive learning signals.
  arXiv  Detail & Related papers  (2026-04-20T13:33:54Z)
• Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards [39.489554597919145]
  Group Relative Policy Optimization (GRPO) assigns a single scalar advantage to all tokens in a completion.<n>For structured generations with explicit segments and objectives, this couples unrelated reward signals across segments, leading to objective interference and misattributed credit.<n>We propose Blockwise Advantage Estimation, a family of GRPO-compatible methods that assigns each objective its own advantage and applies it only to the tokens in the corresponding text block.
  arXiv  Detail & Related papers  (2026-02-10T19:22:37Z)
• MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching [60.886768806064936]
  Tool-Integrated Reasoning empowers large language models to tackle complex tasks by interleaving reasoning steps with external tool interactions.<n>Existing reinforcement learning methods rely on outcome- or trajectory-level rewards, assigning uniform advantages to all steps within a trajectory.<n>We propose MatchTIR, a framework that introduces fine-grained supervision via bipartite matching-based turn-level reward assignment and dual-level advantage estimation.
  arXiv  Detail & Related papers  (2026-01-15T18:59:23Z)
• Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment [87.8301166955305]
  We propose a novel bi-discriminator domain adversarial neural network with class-level gradient alignment. BACG resorts to gradient signals and second-order probability estimation for better alignment of domain distributions. In addition, inspired by contrastive learning, we develop a memory bank-based variant, i.e. Fast-BACG, which can greatly shorten the training process.
  arXiv  Detail & Related papers  (2023-10-21T09:53:17Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Contradictory Structure Learning for Semi-supervised Domain Adaptation [67.89665267469053]
  Current adversarial adaptation methods attempt to align the cross-domain features. Two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain. We propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures.
  arXiv  Detail & Related papers  (2020-02-06T22:58:20Z)

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.