# RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation

arXiv: https://arxiv.org/abs/2610.10120 · HTML: https://mlsanity.com/paper/2610.10120/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 49 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 9 of 9)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents](https://mlsanity.com/paper/2403.08715/) (2024)
- [RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation](https://mlsanity.com/paper/2601.08430/) (2026)
- [AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following](https://mlsanity.com/paper/2511.10507/) (2025)
- [Sotopia-RL: Reward Design for Social Intelligence](https://mlsanity.com/paper/2508.03905/) (2025)
- [Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner](https://mlsanity.com/paper/2406.11978/) (2024)
- [EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation](https://mlsanity.com/paper/2605.29847/) (2026)
- [SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution](https://mlsanity.com/paper/2604.18982/) (2026)

## Abstract (arXiv)

Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in domains where task outcomes can be reliably evaluated, but long-horizon interaction remains challenging due to sparse terminal feedback and difficult credit assignment. Process rewards provide denser supervision, yet the capabilities most relevant for training can change as the policy evolves: a behavior that is easy to evaluate or frequently deficient need not be the bottleneck currently limiting task success. We introduce RewardWeaver, a self-evolving reward adaptation framework for language agents in long-horizon interaction. RewardWeaver maintains a validated capability space in which the semantics of admitted Rubrics remain fixed, and closes the loop between policy optimization, task evaluation, failure attribution, and reward adaptation. After each training stage, it performs outcome-grounded backward attribution on low-outcome trajectories, aggregates recurrent and policy-controlled capability bottlenecks, and dynamically selects the corresponding process rewards for the next stage. Recurrent failures not covered by the existing capability space trigger a separate, controlled expansion procedure. We evaluate REWARDWEAVER on SOTOPIA, Amazon?HistoryPrice, and a newly constructed Sales Benchmark. Across social interaction, bilateral bargaining, and domain-specific sales, REWARDWEAVER establishes new state-of-the-art (SOTA) results. Ablations further demonstrate the importance of dynamic reward allocation, failure-grounded attribution, and stable semantics for admitted capabilities.