Large language model (LLM) agents must generalize from tools seen during training to unseen tools at deployment. A key challenge is tool trialing, i.e., excessive trials waste the interaction budget, whereas selective trials enable exploration of unfamiliar tools. Existing outcome-based post-training leaves wasteful trials unguided, while turn-level supervision may suppress necessary exploration. We introduce ToolCompass, a post-training framework that guides tool trialing by organizing tool-call representations according to shared functions. Specifically, ToolCompass models each function class as a von Mises--Fisher distribution and jointly reduces intra-function variation across domains and increases inter-function separation. This structure transfers experience from seen tools to functionally similar unseen tools, directing exploration away from unrelated alternatives. ToolCompass requires no ground-truth call traces or unseen-tool access and incurs no inference overhead. Experiments on AppWorld and FTRL show consistent gains across GRPO, RFT, and DMPO. improves AppWorld OOD task success by up to 10.71 percentage points over vanilla post-training and performs best among competitive baselines on both benchmarks.
Jun-Lin Fang, Chong-Chong Zhang, Do Nguyen-Thanh et al.· 0 citations
SCOPED-Hiring reveals that balanced final hire rates can mask hidden trajectory unfairness in multi-agent decision trajectories and reduces total layered burden by 72.3% while shifting the hire rate by only 1.86 pp, showing that process diagnosis can guide effective repair.
Yi-Ran Zhao, Lu Zhou, Liming Fang et al.· 0 citations
This work proposes LEAP (Likelihood Elicitation and Aggregation for Probabilistic forecasting), which reorganizes how collected evidence is used in the prediction stage and improves most prediction and calibration metrics across models and remains stronger under controlled comparisons of prior access, inference budget, and aggregation.
Yu-Fei Chen, Yi-Ran Zhao, Xiaogang Xu et al.· 0 citations
Remember-R1 is proposed, a reinforcement learning framework that mitigates long-context visual forgetting by applying process-level supervision directly on the original reasoning trajectory, demonstrating its effectiveness in mitigating long-context visual forgetting.
Jianmin Chen, Jiaqi Tang, Wei Wei et al.· 0 citations
ABE-Ralph is introduced, a reference-anchored auditing framework that represents claims, protocols, required components, baselines, and metrics as structured experimental constraints, guides implementation through an 8-step workflow, and performs quantitative, qualitative, and code-level verification.
Le-Zhi Yu, Xiaogang Xu, Yuhong Zhou et al.· 0 citations
This work investigates LLM-based forecasting agents, meaning systems in which a language model contributes to a scored prediction about a future or currently unobserved target, and organizes architectures into three groups.
Xiaogang Xu, Jiaqi Tang, Jianmin Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
