Research Papers Topics
Methods for steering models toward preferred, safer, or more useful behavior.
Reinforcement Learning · Alibaba Qwen Team
Z-Reward predicts a distribution over rubric scores instead of one scalar. A 9B student hits 88.6% human-preference accuracy with a single output token, and downstream T2I tuning gains 41.3% net GSB over SFT.
Robust-U1 trains an MLLM to reconstruct corrupted visual content, reaching 0.7398 overall on R-Bench versus 0.5770 for BAGEL and 0.5017 for Robust-R1.
AI Agents · Zhejiang University
WeaveBench tests 114 real hybrid GUI plus CLI tasks; the best frontier pairing reaches only 41.2% PassRate, and final-only grading overstates GPT-5.5 by 20.2 points.
Google DeepMind's report lays out four non-exclusive paths from AGI to ASI and treats each bottleneck, from data walls to regulation, as an open research question.
AI Agents · Independent Researcher
AdaPlanBench: Testing Adaptive Planning in LLM Agents turns adaptive planning under constraints into a checkable test, with concrete failure signals, benchmark limits, and builder takeaways.
AI Agents · Independent Researcher
ArcANE: Measuring When Role-Playing Agents Break Character turns role-playing language agent reliability into a checkable test, with concrete failure signals, benchmark limits, and builder takeaways.
Language Models · Independent Researcher
Averaging the output distributions of 3 independent LLMs collapses watermark detection z-scores from 5-300 down below 2, and the WASH paper proves why it works with an O(1/sqrt(N)) error bound.
Reinforcement Learning · Tsinghua University
CHERRL injects four known judge biases to reliably reproduce reward hacking in rubric RL; an agent reading only training logs pinned the onset with 11-step total interval error and missed none of six runs.
AI Agents · Independent Researcher
SoCRATES: Evaluating Proactive LLM Mediation turns proactive mediation agents into a checkable test, with concrete failure signals, benchmark limits, and builder takeaways.
AI Agents · Independent Researcher
TASTE: Harder Agent Benchmarks from Tool Sequences turns tool-use benchmark generation into a checkable test, with concrete failure signals, benchmark limits, and builder takeaways.
AI Agents · Independent Researcher
ToolMaze: When LLM Agents Must Replan After Tool Failures turns dynamic replanning after tool failures into a checkable test, with concrete failure signals, benchmark limits, and builder takeaways.
AI Agents · Shanghai AI Laboratory
AgentDoG 1.5 trains 0.8B-8B agent-safety guard models on only ~1k samples, hits 92.2% accuracy on R-Judge with the 4B variant, rivals GPT-5.4, and cuts agentic-RL deployment overhead by two orders of magnitude.
Constitutional AI trains a harmless assistant with almost no human harm labels. A model critiques and revises its own answers against a written list of principles, then learns from AI-generated preferences (RLAIF).
OpenAI's InstructGPT used human feedback to align GPT-3, and evaluators preferred its 1.3B model over the 175B GPT-3 — more helpful with 100x fewer parameters.
PPO keeps policy-gradient RL stable with a clipped surrogate objective — almost as well-behaved as TRPO but far simpler — which made it the default RL engine behind RLHF for ChatGPT and InstructGPT.
Alignment · Seoul National University
Giving an LLM the Big Five or a values survey predicts almost nothing about how it acts in real queries: cross-method agreement was only Spearman 0.31 (values) and 0.26 (personality), versus 0.74-0.77 within-survey.
Multimodal Models · University of California, Davis
Top video models look like they hear audio but really guess it from the picture. This paper's THUD probes catch the cheat, and a 10K-sample fix lifts audio grounding by 28 points.
Alignment · Stanford University
Direct Preference Optimization solves the RLHF problem with a single classification-style loss on preference pairs: no separate reward model, no RL loop, no sampling during training.