arXiv subjects

Isadora White

Publications and source records attributed to Isadora White.

11 recordsLinked to original sources

arXiv2026

Zephyrus-R1: Agentic Reinforcement Learning for Weather Reporting

Reinforcement learning (RL) has emerged as a key method for training AI models in scientific applications, but RL remains difficult when outputs cannot easily be verified against a known ground-truth answer. Natural-language weather forecast reports are one such domain: they translate atmospheric data into assessments of weather evolution, hazards, and uncertainty for both the general public and key decision-makers. Unlike numerical weather-analysis questions, they admit many valid outputs, which limits deterministic verification. To address this, we develop Zephyrus-R1, a practical framework for RL on scientific weather forecast reporting. We focus on three key components of the agentic RL pipeline: reward design, curriculum learning, and an analysis of human-expert alignment. To encourage both report legibility and factual accuracy, we design a reward function that combines a meteorological rubric with bidirectional claim entailment, both evaluated against National Weather Service reference reports. Our framework optimizes this reward in a simulated tool-calling environment, enabling vision-language agents to gather and analyze forecast evidence across regions and lead times before producing a report. We use annotations from three meteorologists to audit the claim labels produced by our LLM judges. Finally, a curriculum helps small models first develop tool use and scientific reasoning through RL on verifiable weather-analysis questions, then optimize the open-ended report reward. After training Qwen3.5-4B with Zephyrus-R1, we improve the mean across six judge-metric scores by 26% over the base model and achieve results competitive with frontier open-weight models. For Qwen3.8-27B, we improve the same mean by 13% over the base model, by 6.7% over Kimi-K3, and by 2.7% over GPT-5.6-Luna.

cs.LG↗

arXiv2026

Black-Box Forensics for Conversational LLM Agents

As LLM-powered scams proliferate, black-box forensics for conversational LLM agents offers a path to accountability for systems hidden behind anonymous endpoints. Identifying the base model behind a chatbot endpoint (attribution), without model parameter access or knowledge of the hidden system prompt, would let investigators trace AI-enabled scams back to the providers whose models power them. Detecting when two endpoints run the exact same system prompt (fingerprinting), even one novel and unseen, would link individual scams into criminal networks and expose silent API changes. We conduct an empirical investigation of both capabilities. Our attribution classifiers identify the base model behind an agent with 98% accuracy from a few turns of non-adversarial conversation. Attribution of system prompts, while possible, requires retraining on a large amount of data for each prompt; system prompts in the wild are unbounded and ever-changing, making this approach costly. To tackle this more open-ended setting, our cross-encoder fingerprinting method achieves an AUC of 0.768 and an F1 of 0.703 on entirely unseen system prompts, and aggregating 50 interaction conversations from each target agent boosts AUC to 0.943. Conversational agents with unseen system prompts can thus be fingerprinted with robust accuracy from a few turns of ordinary conversation.

cs.CR↗

arXiv2026

Visual Abstention in Unified Multimodal Models

Unified multimodal models (UMMs) integrate understanding and generation, yet their generative behavior is rarely governed by what they understand about the task. We formalize visual abstention: when a requested visual transformation is impossible under the task's rules, the model should recognize that no valid solution exists, state this, and decline to generate. We introduce Draw-or-Decline (DoD), a benchmark of 1,050 feasible-infeasible request pairs across 7 task categories that jointly measures editing success and the refusal of infeasible requests. Evaluating 8 UMMs, we find that editing ability and abstention are distinct capabilities: even the strongest editor, at 68.4% editing accuracy, refuses only 0.4% of infeasible requests under ordinary instructions. Their reasoning shows why: the models rarely notice the conflict, and instead plan the edit as if the request were possible, often describing objects that are not in the image, or quietly change the request into one they can complete. Explicitly prompting these UMMs to report infeasibility increases textual refusals but reduces editing accuracy. We propose VisTA (Visual Transformation and Abstention), a training method that pairs feasible and infeasible examples so that a model judges feasibility before deciding whether to generate. We train VisTA-BAGEL to perform feasible edits and decline infeasible requests. Without any reminder, it refuses 93.0% of infeasible requests, up from 0.4% for the strongest editor, while falsely refusing only 0.8% of feasible ones. Unlike a reminder, this does not cost editing accuracy: VisTA-BAGEL completes 74.3% of feasible edits, more than any of the 8 evaluated UMMs.

cs.CL↗

arXiv2026

FrogNano: Training a 4B Coding Agent via Online Task Synthesis

We present FrogNano, a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively, even under resource-constrained environments. It is post-trained exclusively via RL on around 1,500 SWE environments with synthetic tasks. A key ingredient for improving performance is an online task synthesis pipeline that creates tasks calibrated to the frontier of learnability for the current checkpoint. This report provides evidence that competitive small coding agents can be trained with synthetic tasks alone, without traditional distillation from larger models, and that generating tasks at the learnability frontier of the current agent is important. We report details on the training methodology, evaluations across diverse environments, and in-depth analyses, serving as a foundation for our ongoing exploration of lightweight yet capable coding agents that can run on minimal hardware.

cs.AI↗

arXiv2026

SecureVibe: Making Vibe Coding More Secure

As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern. When investigating functionally correct but insecure solutions, we find that the insecure agent is less than half as likely to conduct effective planning and testing for the hidden security risks behind the functional requirements. Motivated by this, we develop SECUREVIBE, a training recipe that explicitly targets planning and testing for code security. SECUREVIBE constructs training signals around these security behaviors. It includes supervised fine-tuning on the security suite with 4 security tasks, and post-training methods, SECUREVIBE_rl and SECUREVIBE_hg, to enhance security capabilities from verifiable execution feedback and hint-based self-supervision. Our SECUREVIBE outperforms the baseline on two types of security coding tasks across 4 benchmarks. Specifically, SECUREVIBE improves the security pass@1 by 6.9 points on BaxBench. The gains extend to unseen CWE categories, with improvements of 11.5 points on SusVibes. Meanwhile, it also improves functionality pass@1 by 13.6 points on the security coding task SusVibes and 4.1 points on the generic coding task SWE-bench Verified. Further analysis offers two practical insights: (i) diversifying supervision across security planning, coding, and testing strengthens security behaviors more effectively than adding coding trajectories alone, and (ii) hint-guided supervision is particularly valuable when the agent's existing security capabilities are insufficient to learn effectively from outcome feedback.

cs.CR↗

arXiv2026

How LLMs Distort Our Written Language

Large language models (LLMs) are used by over a billion people globally, most often to assist with writing. In this work, we demonstrate that LLMs not only alter the voice and tone of human writing but also consistently alter the intended meaning. First, we conduct a human user study to understand how people actually interact with LLMs when using them for writing. Our findings reveal that extensive LLM use led to a nearly 70% increase in essays that remained neutral in answering the topic question. Significantly more heavy LLM users reported that the writing was less creative and not in their voice. Next, using a dataset of human-written essays that was collected in 2021 before the widespread release of LLMs, we study how asking an LLM to revise the essay based on the human-written feedback in the dataset induces large changes in the resulting content and meaning. We find that even when LLMs are prompted with expert feedback and asked to only make grammar edits, they still change the text in a way that significantly alters its semantic meaning. We then examine LLM-generated text in the wild, specifically focusing on the 21% of AI-generated scientific peer reviews at a recent top AI conference. We find that LLM-generated reviews place significantly less weight on clarity and significance of the research, and assign scores that, on average, are a full point higher. These findings highlight a misalignment between the perceived benefit of AI use and an implicit, consistent effect on the semantics of human writing, motivating future work on how widespread AI writing will affect our cultural and scientific institutions.

cs.CL↗

arXiv2025

Gistify! Codebase-Level Understanding via Runtime Execution

As coding agents are increasingly deployed in large codebases, the need to automatically design challenging, codebase-level evaluation is central. We propose Gistify, a task where a coding LLM must create a single, minimal, self-contained file that can reproduce a specific functionality of a codebase. The coding LLM is given full access to a codebase along with a specific entrypoint (e.g., a python command), and the generated file must replicate the output of the same command ran under the full codebase, while containing only the essential components necessary to execute the provided command. Success on Gistify requires both structural understanding of the codebase, accurate modeling of its execution flow as well as the ability to produce potentially large code patches. Our findings show that current state-of-the-art models struggle to reliably solve Gistify tasks, especially ones with long executions traces.

cs.CL↗

arXiv2025

BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills

High quality bugs are key to training the next generation of language model based software engineering (SWE) agents. We introduce a novel method for synthetic generation of difficult and diverse bugs. Our method instructs SWE Agents to introduce a feature into the codebase whereby they may unintentionally break tests, resulting in bugs. Prior approaches often induce an out-of-distribution effect by generating bugs intentionally (e.g. by introducing local perturbation to existing code), which does not reflect realistic development processes. We perform qualitative analysis to demonstrate that our approach for generating bugs more closely reflects the patterns found in human-authored edits. Through extensive experiments, we demonstrate that our bugs provide more efficient training data for supervised fine-tuning, outperforming other bug datasets by 2% with half the training data (1.2k vs. 3k bugs). We train on our newly generated bugs in addition to existing bug datasets to get FrogBoss a state-of-the-art 32B parameter model on SWE-bench Verified with a pass@1 of 54.6% and FrogMini a state-of-the-art 14B model on SWE-bench Verified with a pass@1 of 45.3% on SWE-bench Verified averaged over three seeds.

cs.SE↗

arXiv2025

Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning

Collaboration is ubiquitous and essential in day-to-day life -- from exchanging ideas, to delegating tasks, to generating plans together. This work studies how LLMs can adaptively collaborate to perform complex embodied reasoning tasks. To this end we introduce MINDcraft, an easily extensible platform built to enable LLM agents to control characters in the open-world game of Minecraft; and MineCollab, a benchmark to test the different dimensions of embodied and collaborative reasoning. An experimental study finds that the primary bottleneck in collaborating effectively for current state-of-the-art agents is efficient natural language communication, with agent performance dropping as much as 15% when they are required to communicate detailed task completion plans. We conclude that existing LLM agents are ill-optimized for multi-agent collaboration, especially in embodied scenarios, and highlight the need to employ methods beyond in-context and imitation learning. Our website can be found here: https://mindcraft-minecollab.github.io/

cs.MA↗

arXiv2024

Communicate to Play: Pragmatic Reasoning for Efficient Cross-Cultural Communication in Codenames

Cultural differences in common ground may result in pragmatic failure and misunderstandings during communication. We develop our method Rational Speech Acts for Cross-Cultural Communication (RSA+C3) to resolve cross-cultural differences in common ground. To measure the success of our method, we study RSA+C3 in the collaborative referential game of Codenames Duet and show that our method successfully improves collaboration between simulated players of different cultures. Our contributions are threefold: (1) creating Codenames players using contrastive learning of an embedding space and LLM prompting that are aligned with human patterns of play, (2) studying culturally induced differences in common ground reflected in our trained models, and (3) demonstrating that our method RSA+C3 can ease cross-cultural communication in gameplay by inferring sociocultural context from interaction. Our code is publicly available at github.com/icwhite/codenames.

cs.CL↗

arXiv2023

LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models

Large language models (LLMs) provide excellent text-generation capabilities, but standard prompting and generation methods generally do not lead to intentional or goal-directed agents and might necessitate considerable prompt tuning. This becomes particularly apparent in multi-turn conversations: even the best current LLMs rarely ask clarifying questions, engage in explicit information gathering, or take actions now that lead to better decisions after multiple turns. Reinforcement learning has the potential to leverage the powerful modeling capabilities of LLMs, as well as their internal representation of textual interactions, to create capable goal-directed language agents. This can enable intentional and temporally extended interactions, such as with humans, through coordinated persuasion and carefully crafted questions, or in goal-directed play through text games to bring about desired final outcomes. However, enabling this requires the community to develop stable and reliable reinforcement learning algorithms that can effectively train LLMs. Developing such algorithms requires tasks that can gauge progress on algorithm design, provide accessible and reproducible evaluations for multi-turn interactions, and cover a range of task properties and challenges in improving reinforcement learning algorithms. Our paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for LLMs, together with an open-source research framework containing a basic toolkit for getting started on multi-turn RL with offline value-based and policy-based RL methods. Our benchmark consists of 8 different language tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.

cs.CL↗