Roshni Iyer

Shashank Kirtania, Param Biyani, Priyanshu Gupta et al.

Large Language Model (LLM)-based agents are increasingly applied to tasks requiring structured reasoning, tool use, and environmental adaptation, such as data manipulation, multistep planning, and computer-use automation. However, despite their versatility, current training paradigms for model weight optimization methods, like PPO and GRPO, remain relatively impractical with their high computational overhead for rollout convergence. In addition, the resulting agent policies are difficult to interpret, adapt, or incrementally improve. To address this, we investigate creating and refining structured memory of experiential learning of an agent from its environment as an alternative route to agent optimization. We introduce BREW (Bootstrapping expeRientially-learned Environmental knoWledge), a framework for agent optimization for downstream tasks via KB construction and refinement. In our formulation, we introduce an effective method for partitioning agent memory for more efficient retrieval and refinement. BREW uses task graders and behavior rubrics to learn insights while leveraging state-space search for ensuring robustness from the noise and non-specificity in natural language. Empirical results on real world, domain-grounded benchmarks -- OSWorld, $τ^2$Bench, and SpreadsheetBench -- show BREW achieves $10-20\%$ improvement in task precision, $10-15\%$ reduction in API/tool calls leading to faster execution time, all while maintaining computational efficiency on par with base models. Unlike prior work where memory is treated as static context, we establish the KB as a modular and controllable substrate for agent optimization -- an explicit lever for shaping behavior in a transparent, interpretable, and extensible manner.

Khiem Le, Zhichun Guo, Kaiwen Dong et al.

Large Language Models (LLMs) with their strong task-handling capabilities have shown remarkable advancements across a spectrum of fields, moving beyond natural language understanding. However, their proficiency within the chemistry domain remains restricted, especially in solving molecule-related tasks. This challenge is attributed to their inherent limitations in comprehending molecules using only common textual representations, i.e. SMILES strings. In this study, we seek to enhance the ability of LLMs to comprehend molecules by equipping them with a multi-modal external module, termed MolX. Instead of directly using SMILES strings to represent a molecule, we utilize specific encoders to extract fine-grained features from both SMILES string and 2D molecular graph representations for feeding into an LLM. A hand-crafted molecular fingerprint is incorporated to leverage its embedded domain knowledge. To establish an alignment between MolX and the LLM's textual input space, the model in which the LLM is frozen, is pre-trained with a strategy including a diverse set of tasks. Experimental evaluations show that our proposed method outperforms baselines across downstream molecule-related tasks ranging from molecule-to-text translation to molecular property prediction, with and without fine-tuning the LLM, while only introducing a small number of trainable parameters-0.53% and 0.82%, respectively.