arXiv cs.CL· Yue Leng, Shengtao Wen, Xiang Chen, Xinyi Zeng, Yu Tian, Sheng-Jun Huang·· 11 小时前AI 评分26
CREDO：面向时序推理智能体的证据条件化信用分配方法
CREDO: Evidence-Conditioned Credit Assignment for Temporal Reasoning Agents
AI 导读
CREDO 通过中间证据恢复局部监督信号，解决 GRPO 轨迹级奖励无法区分中间决策质量的问题，在全部失败组中也能重新分配信用。在 MultiTQ 上，CREDO 将 Overall 准确率从 78.0% 提升至 82.4%，Multiple 准确率从 55.0% 提升至 65.6%；在 TimelineKGQA 上，跨 KG 准确率从 30.9% 提升至 36.4%。
正文 · 原文
Abstract:Temporal Knowledge Graph Question Answering (TKGQA) requires language model agents to retrieve evidence, select relevant facts, and perform multi-step temporal reasoning. However, the trajectory-level outcome signal in GRPO does not explicitly distinguish the quality of intermediate decisions: downstream failures can penalize useful evidence acquisition, while identical rewards in all-failed groups eliminate the relative outcome signal despite differences in intermediate progress. We propose Credit Redistribution with Evidence-Driven Opportunities (CREDO), which uses intermediate evidence to recover local supervision, including in all-failed groups, and determine where outcome supervision acts. CREDO assigns positive stage-level credit through comparisons among rollouts of the same question and uses retained answer overlap as an opportunity proxy to shift part of the outcome-policy weight toward reasoning and answering. The framework preserves terminal rewards and trajectory-level advantages, while redistribution conserves total outcome-policy weight per trajectory. Following the public evaluation protocol of prior work, CREDO raises Overall accuracy from 78.0% to 82.4% and Multiple accuracy from 55.0% to 65.6% on MultiTQ relative to the strongest published baseline in our comparison. On TimelineKGQA, it raises cross-KG accuracy from 30.9% to 36.4% relative to our reproduced baseline via direct transfer to ICEWS Actor under matched training and evaluation settings.
| Comments: | Code available at this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2611.01643 [cs.LG] |
| (or arXiv:2611.01643v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01643 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shengtao Wen [view email]
[v1]
Sun, 1 Nov 2026 06:46:51 UTC (733 KB)
来源：arXiv cs.CL · arxiv.org