Long-horizon LLM agents require memory systems that recover useful evidence from large interaction histories without passing excessive context to downstream models. Existing memory pipelines often rely on hand-crafted heuristics and repeated LLM calls, which can introduce redundant context and high inference cost. We propose MemoryCPT, an end-to-end trainable agent memory pipeline that spans offline memory construction and online query-conditioned context generation. MemoryCPT consists of two stages: Query-agnostic Distillation (QAD), which distills a modular memory-construction pipeline into a compact model using explicit reasoning traces; and Query-aware Retrieval and Summarization (QAR), which combines reciprocal rank fusion (RRF) with a LoRA-based summarizer trained via Group Relative Policy Optimization (GRPO) under a cost-aware reward. We further introduce Quality per Cost (QPC) to quantify answer quality per unit inference cost. Experiments on LoCoMo and LongMemEval show that MemoryCPT improves the cost-performance trade-off over the evaluated baselines, while ablation and sensitivity analyses characterize the contributions of its components and the effects of key design choices.
Songxin Lei, Kun Ouyang, Weilin Ruan et al.· 0 citations
Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, overlooking that scientific analysis serves to support distinct types of scientific claims: hypothesis exploration, statistical inference, mechanistic explanation, each with different assumptions and validity criteria. We introduce SDABench, a benchmark that reorganizes evaluation around six capabilities (descriptive, exploratory, inferential, predictive, causal, and mechanistic) across five domains (Biology, Chemistry, Environment, Geography, Physics). SDABench comprises 527 real-data instances (SDA-Real) and 6000 synthetic instances (SDA-Synth), each in both multiple-choice and open-ended formats, constructed through an automated pipeline. Evaluating 15 representative LLMs, we find that models handle descriptive analysis well but degrade sharply on tasks requiring assumption selection, latent-process modeling, or mechanistic reasoning. SDABench further provides a five-stage error analysis framework that locates where LLMs fail: more advanced models more reliably identify the relevant scope and variables, but still struggle to select appropriate analytical procedures, model variable relationships, and draw valid conclusions.
Chuhan Shi, Xiaoquan Ren, Sicheng Song et al.· 1 citation
Small-molecule drug discovery relies on iterative molecular optimization, where chemists repeatedly modify candidate compounds to balance multiple competing properties such as efficacy, toxicity, and solubility. Recent advances in generative AI (GenAI) have shown promise in accelerating this process by automatically proposing new molecular structures or targeted modifications. However, existing GenAI-based molecular design tools remain poorly aligned with experts'real-world workflows. Specifically, they offer limited support for specifying structure-level modification intents on molecules, provide insufficient transparency into model-generated modifications, and lack integrated support for downstream property evaluation with external computational tools. To address these challenges, we introduce MolecularCanvas, an interactive system that enables users to iteratively construct an optimization context by integrating high-level goals, structure-level annotations, property constraints, and reference-based preferences. This context guides the generation of candidate molecules across diverse molecular structures. MolecularCanvas further enhances transparency by providing evidence for AI-generated suggestions and streamlines molecular evaluation by integrating commonly used computational tools for property assessment into a unified interface. Finally, a user study with 12 participants demonstrates the usefulness and effectiveness of MolecularCanvas in helping users optimize candidate molecules.
Haoyu Dong, Rui Sheng, Shuhao Zhang et al.· 0 citations