The AI Scientist framework enables LLMs to independently conduct the full scientific process from idea generation to paper writing and review, demonstrated across three ML subfields with papers costing under $15 each.
Canonical reference
Title resolution pending
Canonical reference. 100% of citing Pith papers cite this work as background.
23
Pith papers citing it
Background
100% of classified citations
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
Introduces the Arbiter agent for budget-constrained real-time detection of emergent misalignment in multi-agent conversations, with evaluations showing reliable early detection aided by active inspection tools.
In two-layer networks, weak-to-strong training elicits the target feature direction from pre-trained subspaces and preserves correlated off-target features, unlike standard fine-tuning.
MLLMs display a large perception-reasoning gap on perspective-conditioned spatial reasoning tasks from omnidirectional images, with sharp accuracy drops on advanced tasks like egocentric rotation, though partial gains are possible via RL reward shaping.
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
Introduces AIR, an asymmetric regularization that anchors open-ended safety prompts to verifiable ones via stop-gradient, improving invariance and accuracy when combined with group preference optimization.
Base LLMs show multi-agent yield to peer pressure at rates equal to or higher than aligned models, localized by activation patching to mid-layers where attention dominates, with one dissenter cutting yield by 54-73 points while prompt defenses fail on variants.
AI agents automating alignment research are prone to systematic undetected errors in fuzzy tasks, leading to overconfident but flawed safety assessments even without deliberate sabotage.
For heterogeneous power-p pseudospherical scoring rules with d ≤ 4, the True-KL0 property R(M,p,d) < 1 holds for all M > 1, establishing unconditional DSIC via a Prekopa-based log-concavity argument on the loss integral.
AI alignment is reframed as a fixed-point incentive problem in a solver-auditor pipeline, solved via bilevel optimization and bandit search over reward profiles to maintain monitoring and reduce hallucinations in LLM coding tasks.
Weak supervision supports in-domain prediction of guide efficacy in CRISPR-Cas13d data but collapses under temporal shifts due to changing feature-label associations, while cross-cell-line transfer remains partial.
Fine-tuned LLM judges struggle with future-proofing to newer generators but maintain backward-compatibility more easily; DPO training and continual learning improve adaptation while all models degrade on unseen questions.
Sparse feature circuits are introduced as interpretable causal subnetworks in language models, supporting unsupervised discovery of thousands of circuits and a method called SHIFT to improve classifier generalization by ablating irrelevant features.
DeepSeekMath 7B reaches 51.7% on MATH via continued pretraining on curated web math data and Group Relative Policy Optimization.
Echo is a framework that harvests user-driven refinements of agent proposals as training signals to align models with real-world needs, demonstrated by raising code completion acceptance from 25.7% to 35.7% in production.
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.
Introduces a latent user quality model and EM algorithm to infer and filter noisy user-provided pairwise preferences for improved LLM alignment.
WildFeedback extracts preference pairs from in-situ user feedback in LLM conversations to fine-tune models for better alignment with real user preferences.
DenoiseRL optimizes recovery from noisy prefixes in weak-model reasoning failures to improve performance and self-correction on math and general reasoning benchmarks without external supervision.
Frontier AI needs contextual multi-objective optimization to select and balance multiple context-dependent objectives rather than relying on single stable goals.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
citing papers explorer
-
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
The AI Scientist framework enables LLMs to independently conduct the full scientific process from idea generation to paper writing and review, demonstrated across three ML subfields with papers costing under $15 each.
-
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment
Introduces the Arbiter agent for budget-constrained real-time detection of emergent misalignment in multi-agent conversations, with evaluations showing reliable early detection aided by active inspection tools.
-
The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
In two-layer networks, weak-to-strong training elicits the target feature direction from pre-trained subspaces and preserves correlated off-target features, unlike standard fine-tuning.
-
Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images
MLLMs display a large perception-reasoning gap on perspective-conditioned spatial reasoning tasks from omnidirectional images, with sharp accuracy drops on advanced tasks like egocentric rotation, though partial gains are possible via RL reward shaping.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
Towards Context-Invariant Safety Alignment for Large Language Models
Introduces AIR, an asymmetric regularization that anchors open-ended safety prompts to verifiable ones via stop-gradient, improving invariance and accuracy when combined with group preference optimization.
-
Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy
Base LLMs show multi-agent yield to peer pressure at rates equal to or higher than aligned models, localized by activation patching to mid-layers where attention dominates, with one dissenter cutting yield by 54-73 points while prompt defenses fail on variants.
-
Automated alignment is harder than you think
AI agents automating alignment research are prone to systematic undetected errors in fuzzy tasks, leading to overconfident but flawed safety assessments even without deliberate sabotage.
-
Honest Reporting in Scored Oversight: True-KL0 Property via the Prekopa Principle
For heterogeneous power-p pseudospherical scoring rules with d ≤ 4, the True-KL0 property R(M,p,d) < 1 holds for all M > 1, establishing unconditional DSIC via a Prekopa-based log-concavity argument on the loss integral.
-
AI Alignment via Incentives and Correction
AI alignment is reframed as a fixed-point incentive problem in a solver-auditor pipeline, solved via bilevel optimization and bandit search over reward profiles to maintain monitoring and reduce hallucinations in LLM coding tasks.
-
Learning Stable Predictors from Weak Supervision under Distribution Shift
Weak supervision supports in-domain prediction of guide efficacy in CRISPR-Cas13d data but collapses under temporal shifts due to changing feature-label associations, while cross-cell-line transfer remains partial.
-
On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization
Fine-tuned LLM judges struggle with future-proofing to newer generators but maintain backward-compatibility more easily; DPO training and continual learning improve adaptation while all models degrade on unseen questions.
-
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
Sparse feature circuits are introduced as interpretable causal subnetworks in language models, supporting unsupervised discovery of thousands of circuits and a method called SHIFT to improve classifier generalization by ablating irrelevant features.
-
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
DeepSeekMath 7B reaches 51.7% on MATH via continued pretraining on curated web math data and Group Relative Policy Optimization.
-
Echo: Learning from Experience Data via User-Driven Refinement
Echo is a framework that harvests user-driven refinements of agent proposals as training signals to align models with real-world needs, demonstrated by raising code completion acceptance from 25.7% to 35.7% in production.
-
Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.
-
Users as Annotators: LLM Preference Learning from Comparison Mode
Introduces a latent user quality model and EM algorithm to infer and filter noisy user-provided pairwise preferences for improved LLM alignment.
-
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback
WildFeedback extracts preference pairs from in-situ user feedback in LLM conversations to fine-tune models for better alignment with real user preferences.
-
DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes
DenoiseRL optimizes recovery from noisy prefixes in weak-model reasoning failures to improve performance and self-correction on math and general reasoning benchmarks without external supervision.
-
Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems
Frontier AI needs contextual multi-objective optimization to select and balance multiple context-dependent objectives rather than relying on single stable goals.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
- Weak-to-Strong Elicitation via Mismatched Wrong Drafts
- Generalizable Video Quality Assessment via Weak-to-Strong Learning