Ashwin Gopinath

Noah Shinn, Federico Cassano, Edward Berman et al.

Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning. We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback. Concretely, Reflexion agents verbally reflect on task feedback signals, then maintain their own reflective text in an episodic memory buffer to induce better decision-making in subsequent trials. Reflexion is flexible enough to incorporate various types (scalar values or free-form language) and sources (external or internally simulated) of feedback signals, and obtains significant improvements over a baseline agent across diverse tasks (sequential decision-making, coding, language reasoning). For example, Reflexion achieves a 91% pass@1 accuracy on the HumanEval coding benchmark, surpassing the previous state-of-the-art GPT-4 that achieves 80%. We also conduct ablation and analysis studies using different feedback signals, feedback incorporation methods, and agent types, and provide insights into how they affect performance.

Sravya Vardhani Shivapuja, Ashwin Gopinath, Ayush Gupta et al.

The data distribution in popular crowd counting datasets is typically heavy tailed and discontinuous. This skew affects all stages within the pipelines of deep crowd counting approaches. Specifically, the approaches exhibit unacceptably large standard deviation wrt statistical measures (MSE, MAE). To address such concerns in a holistic manner, we make two fundamental contributions. Firstly, we modify the training pipeline to accommodate the knowledge of dataset skew. To enable principled and balanced minibatch sampling, we propose a novel smoothed Bayesian binning approach. More specifically, we propose a novel cost function which can be readily incorporated into existing crowd counting deep networks to encourage bin-aware optimization. As the second contribution, we introduce additional performance measures which are more inclusive and throw light on various comparative performance aspects of the deep networks. We also show that our binning-based modifications retain their superiority wrt the newly proposed performance measures. Overall, our contributions enable a practically useful and detail-oriented characterization of performance for crowd counting approaches.

Sambartha Ray Barman, Andrey Starenky, Sofia Bodnar et al.

Every major AI memory system in production today organises information by meaning. That organisation enables generalisation, analogy, and conceptual retrieval -- but it comes at a price. We prove that the same geometric structure enabling semantic generalisation makes interference, forgetting, and false recall inescapable. We formalise this tradeoff for \textit{semantically continuous kernel-threshold memories}: systems whose retrieval score is a monotone function of an inner product in a semantic feature space with finite local intrinsic dimension. Within this class we derive four results: (1) semantically useful representations have finite effective rank; (2) finite local dimension implies positive competitor mass in retrieval neighbourhoods; (3) under growing memory, retention decays to zero, yielding power-law forgetting curves under power-law arrival statistics; (4) for associative lures satisfying a $δ$-convexity condition, false recall cannot be eliminated by threshold tuning. We test these predictions across five architectures: vector retrieval, graph memory, attention-based context, BM25 filesystem retrieval, and parametric memory. Pure semantic systems express the vulnerability directly as forgetting and false recall. Reasoning-augmented systems partially override these symptoms but convert graceful degradation into catastrophic failure. Systems that escape interference entirely do so by sacrificing semantic generalisation. The price of meaning is interference, and no architecture we tested avoids paying it.

Sambartha Ray Barman, Andrey Starenky, Sophia Bodnar et al.

Why do we forget? Why do we remember things that never happened? The conventional answer points to biological hardware. We propose a different one: geometry. Here we show that high-dimensional embedding spaces, subjected to noise, interference, and temporal degradation, reproduce quantitative signatures of human memory with no phenomenon-specific engineering. Power-law forgetting ($b = 0.460 \pm 0.183$, human $b \approx 0.5$) arises from interference among competing memories, not from decay. The identical decay function without competitors yields $b \approx 0.009$, fifty times smaller. Time alone does not produce forgetting in this system. Competition does. Production embedding models (nominally 384--1{,}024 dimensions) concentrate their variance in only ${\sim}16$ effective dimensions, placing them deep in the interference-vulnerable regime. False memories require no engineering at all: cosine similarity on unmodified pre-trained embeddings reproduces the Deese--Roediger--McDermott false alarm rate ($0.583$ versus human ${\sim}0.55$) with zero parameter tuning and no boundary conditions. We did not build a false memory system. We found one already present in the raw geometry of semantic space. These results suggest that core memory phenomena are not bugs of biological implementation but features of any system that organizes information by meaning and retrieves it by proximity.

Tyler D. Ross, Ashwin Gopinath

The future development of an AI scientist, a tool that is capable of integrating a variety of experimental data and generating testable hypotheses, holds immense potential. So far, bespoke machine learning models have been created to specialize in singular scientific tasks, but otherwise lack the flexibility of a general purpose model. Here, we show that a general purpose large language model, chatGPT 3.5-turbo, can be fine-tuned to learn the structural biophysics of DNA. We find that both fine-tuning models to return chain-of-thought responses and chaining together models fine-tuned for subtasks have an enhanced ability to analyze and design DNA sequences and their structures.

Orion Li, Vinayak Agarwal, Summer Zhou et al.

The complexity of modern bioinformatics analysis has created a critical gap between data generation and developing scientific insights. While large language models (LLMs) have shown promise in scientific reasoning, they remain fundamentally limited when dealing with real-world analytical workflows that demand iterative computation, tool integration and rigorous validation. We introduce K-Dense Analyst, a hierarchical multi-agent system that achieves autonomous bioinformatics analysis through a dual-loop architecture. K-Dense Analyst, part of the broader K-Dense platform, couples planning with validated execution using specialized agents to decompose complex objectives into executable, verifiable tasks within secure computational environments. On BixBench, a comprehensive benchmark for open-ended biological analysis, K-Dense Analyst achieves 29.2% accuracy, surpassing the best-performing language model (GPT-5) by 6.3 percentage points, representing nearly 27% improvement over what is widely considered the most powerful LLM available. Remarkably, K-Dense Analyst achieves this performance using Gemini 2.5 Pro, which attains only 18.3% accuracy when used directly, demonstrating that our architectural innovations unlock capabilities far beyond the underlying model's baseline performance. Our insights demonstrate that autonomous scientific reasoning requires more than enhanced language models, it demands purpose-built systems that can bridge the gap between high-level scientific objectives and low-level computational execution. These results represent a significant advance toward fully autonomous computational biologists capable of accelerating discovery across the life sciences.