◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Daniel Donnelly

4 papers hereh-index 6228 citations41 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author2
  • middle author1

Across the 3 of 4 papers where every author was matched, so the position is known.

fields
  • cs.AI1
  • cs.CL1
  • cs.CR1
  • cs.LG1

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.CL2026

A Model Organism for Studying Unverbalized Evaluation Awareness

Daniel Donnelly, Evan Chapple, Haritz Puerto +1

Large language models can recognize when they are being evaluated and change their behavior accordingly, undermining the reliability of safety benchmarks. Evaluation awareness (EA)…

cs.CR2026

SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents

Saswat Das, Parvati Viswanathan, Daniel Donnelly +3

Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their controller instructions, memory management…

cs.AI2026

ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D

Lena Libon, Ben Rank, Jehyeok Yeon +5

As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted. AI control offers one such…

cs.LG2025

Expressive Reward Synthesis with the Runtime Monitoring Language

Daniel Donnelly, Angelo Ferrando, Francesco Belardinelli

A key challenge in reinforcement learning (RL) is reward (mis)specification, whereby imprecisely defined reward functions can result in unintended, possibly harmful, behaviours. In…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.