Amazon Science

Current MLLMs struggle with Bangla form comprehension, missing key granular details that could hinder their real-world application in low-resource languages.

Current speech-to-speech models may sound good, but they miss the mark on natural conversational dynamics, revealing critical areas for improvement.

AutoRestTest outperformed all competitors in the SBFT 2026 Tool Competition, revealing significant advancements in automated REST API testing.

A unified creativity benchmark reveals that LLMs exhibit a single creativity factor, yet top human creators still outperform them in creative tasks.

Matched reference regimes for prosody evaluation reveal that traditional methods over-flag deviations, leading to misinterpretations in speech AI assessments.

Data referencing errors plague LLMs even in structured tasks, but a lightweight critic model can boost accuracy by up to 12%.

Advanced RAG methods like GraphRAG and Agentic RAG can reduce token usage by up to 53%, but they don't always enhance generation quality as expected.

Exact-match retrieval metrics can mislead assessments of policy utility, as retrieved clauses perform nearly as well as gold-standard ones in decision-making tasks.

All tested coding agents fail within 5-6 turns, but providing feedback can boost their performance by up to 12x, revealing critical insights into agent design.

Semantic progress in dialogue can be quantified effectively without relying on large models, achieving human-level agreement on information gain across turns.

High-performance ML models can be reproduced with minimal information, revealing that they thrive in low-complexity regions and defy traditional overfitting concerns.

Sustained self-improvement in LLM agents is achievable through a novel adaptive framework that outperforms traditional methods in dynamic task environments.

LLMs can resolve merge conflicts nearly as well as Google's best, but still fail in over 40% of cases, revealing a surprising bottleneck in automating software development.

Targeted neuro-symbolic integration can reduce content bias in syllogistic reasoning, achieving over 94% accuracy while cutting content effects by 16%.

RAG systems are stuck in a factual echo chamber, ignoring the rich tapestry of opinions that shape real-world understanding.

LLMs can now autonomously translate entire C projects to Rust with near-perfect accuracy, thanks to a novel agentic framework that dynamically navigates dependencies and iteratively verifies translations.

Domain-specific fine-tuning can induce "agentic collapse" in LLMs, but a surprisingly small amount of agentic data from *another* domain can bring those general tool-use skills roaring back.

Forget wrestling with language-specific tooling: ReCodeAgent autonomously translates and validates entire code repositories across diverse languages with a 60% boost in test pass rates.

LLMs aren't culture-aware reasoners, but biased translators: they generate stereotyped metaphors and default to Western perspectives even when prompted with specific cultural identities.

LLMs can automatically generate web vulnerability detection rules with surprisingly high accuracy, but only with careful validation and human oversight to mitigate overconfidence.

LLM-generated survey responses can be statistically accurate yet still miss the option most preferred by humans, highlighting a critical flaw in current evaluation methods.

Forget expensive multilingual annotations: this framework lets you evaluate LLMs in new languages by transferring knowledge from English, with surprisingly strong results.

Save 20% on LLM costs with <2% accuracy drop by strategically cascading a small model with a large one, guided by a confidence-calibrated SLM.

LLMs can ace math problems while reasoning like a drunk toddler, with 82% of correct answers arising from unstable, inconsistent logic.

Safety classifiers for LLMs can catastrophically fail with even minuscule embedding drift, creating dangerous blind spots in deployed safety architectures.

Despite matching or exceeding human expert performance on generating potential diagnoses, current MLLMs struggle to synthesize multimodal clinical evidence for final diagnosis, revealing a critical gap in their clinical reasoning abilities.

Forget Bonferroni: a new sequential testing approach slashes audit times for multi-stream ML systems, especially when anomalies are widespread.

Latent reasoning models often take shortcuts to achieve high accuracy, and stronger supervision, while mitigating this, paradoxically restricts the diversity of their latent representations.

Forget fine-tuning: inject targeted time-series insights into general LLMs and watch their reasoning skills skyrocket by up to 26%.

Object hallucination in MLLMs can be significantly reduced by simply masking salient visual features during contrastive decoding.

LLMs evaluating job candidates exhibit significant bias against hedging language, docking candidates by 25.6% on average, even when the content is equivalent.