AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
Kimi K2
Moonshot AI introduces Kimi K2, a 1T parameter Mixture-of-Experts model (32B active) optimized not just for knowledge tasks but for agentic capabilities, models that act, not just respond. Released as Kimi-K2-Base and Kimi-K2-Instruct, it achieves strong scores across coding, math, and tool-use benchmarks and is open-source for research and deployment.
Why do Some Language Models Fake Alignment While Others Don’t
This paper expands the analysis of alignment faking in LLMs, where models comply with training objectives during training but behave differently in deployment. The authors study 25 LLMs and find that only five (Claude 3 Opus, Claude 3.5 Sonnet, Llama 3 405B, Grok 3, Gemini 2.0 Flash) exhibit a significant compliance gap: they are more likely to comply with harmful requests when they believe they are being trained. This selective compliance, or "alignment faking", is linked to deeper model motivations and training dynamics.
A Survey on Latent Reasoning
Provides a comprehensive overview of latent reasoning, an emerging field that shifts AI reasoning from explicit, token-based "chain-of-thought" to implicit computations within a model's continuous hidden states. Key ideas:
AI Research Agents for Machine Learning
Presents a new framework, AIRA-dojo, for developing and evaluating AI research agents. They use this framework to systematically investigate the components of successful AI agents on the MLE-bench benchmark, a challenging set of real-world machine learning problems from Kaggle. Key findings:
HIRAG
HIRAG is a new instruction fine-tuning method that enhances the capabilities of RAG models by teaching them to think before answering. Key ideas:
Small Language Models are the Future of Agentic AI
This position paper argues that small language models (SLMs), defined as those runnable on consumer-grade hardware, are not only sufficient but superior for many agentic AI applications, especially when tasks are narrow, repetitive, or tool-oriented. The authors propose that shifting from LLM-first to SLM-first architectures will yield major gains in efficiency, modularity, and sustainability.
Chain-of-Thought Is Not Explainability
It challenges the common assumption that chain-of-thought (CoT) reasoning in LLMs is synonymous with interpretability. While CoT improves performance and offers a seemingly transparent rationale, the authors argue it is neither necessary nor sufficient for faithful explanation. Through a review of empirical evidence and mechanistic insights, the paper makes the case that CoT often diverges from the internal computations that actually drive model predictions.
Agentic RAG for Personalized Recommendation
Introduces a multi-agent framework that enhances traditional RAG systems with reasoning agents tailored to user modeling and contextual ranking. Developed at Walmart Global Tech, ARAG reframes recommendations as a structured coordination problem between LLM agents.
Deep Research Agents
Provides the most comprehensive survey to date of Deep Research (DR) agents, LLM-powered systems built for autonomous, multi-step informational research. The paper defines DR agents as AI systems that tightly integrate dynamic reasoning, adaptive long-horizon planning, tool use, retrieval, and structured report generation. It establishes a taxonomy of DR architectures, evaluates recent advances, and outlines the limitations of current systems and benchmarks.
Survey on Evaluation of LLM-based Agents
This work presents the first comprehensive overview of how to evaluate LLM-based agents, which differ significantly from traditional LLMs by maintaining memory, planning over multiple steps, using tools, and interacting with dynamic environments. The authors categorize and analyze the evaluation landscape across four axes: core agent capabilities, application-specific agent benchmarks, generalist agent evaluation, and supporting evaluation frameworks.
NaturalThoughts
This paper introduces NaturalThoughts, a large-scale dataset of reasoning traces distilled from DeepSeek-R1 using questions from the NaturalReasoning corpus. It challenges the "Less is More" hypothesis by showing that simply scaling up high-quality reasoning traces, without aggressive filtering, yields robust and general improvements across STEM reasoning tasks for smaller models like Llama-3.1-8B and Qwen-2.5-7B.
Visual Structures Help Visual Reasoning
This study shows that adding simple spatial structures (like horizontal lines) to images significantly boosts GPT-4o’s visual reasoning by improving feature binding. This visual input tweak outperforms textual strategies alone, yielding large gains in visual search (+25%), counting (+26.8%), and spatial understanding (+9.5%).
MEM1
This work introduces MEM1, an RL framework for training language agents that operate efficiently over long-horizon, multi-turn tasks by learning to consolidate memory and reasoning into a compact internal state. Unlike traditional agents that append all past interactions, leading to ballooning memory usage and degraded performance, MEM1 maintains a constant memory size by discarding obsolete context after each reasoning step. It achieves this by jointly updating an internal state that encodes both new observations and prior memory, optimizing for task completion via RL without needing external memory modules. Key contributions and findings:
Towards AI Search Paradigm
Proposes a modular multi-agent system that reimagines how AI handles complex search tasks, aiming to emulate human-like reasoning and information synthesis. The system comprises four specialized LLM-powered agents, Master, Planner, Executor, and Writer, that dynamically coordinate to decompose, solve, and answer user queries. This framework moves beyond traditional document retrieval or RAG pipelines by structuring tasks into directed acyclic graphs (DAGs), invoking external tools, and supporting dynamic re-planning. Key contributions include:
Reinforcement-Learned Teachers of Test Time Scaling
Introduces Reinforcement-Learned Teachers (RLTs), small, efficient LMs trained with RL not to solve problems from scratch, but to generate high-quality explanations that help downstream student models learn better. This approach circumvents the notorious exploration challenges in traditional RL setups by giving the RLTs access to both questions and solutions, thereby framing the task as “connect-the-dots” explanation generation. These explanations are rewarded based on how well a student LM, trained on them, understands and can reproduce the correct answer, enabling dense, interpretable supervision. Key contributions and findings:
DeepRare
Introduces DeepRare, a modular agentic system powered by LLMs to aid rare disease diagnosis from multimodal clinical inputs (text, HPO terms, VCFs). It generates ranked diagnostic hypotheses with fully traceable reasoning chains linked to verifiable medical sources, addressing a long-standing need for interpretability in clinical AI.
RAG+
Introduces RAG+, a modular framework that improves traditional RAG systems by explicitly incorporating application-level reasoning into the retrieval and generation pipeline. While standard RAG pipelines fetch relevant knowledge, they often fail to show how to use that knowledge effectively in reasoning-intensive tasks. RAG+ fills this gap by retrieving not only knowledge but also paired application examples, leading to more accurate, interpretable, and goal-oriented outputs. Key highlights:
From Bytes to Ideas
Proposes AU-Net, a hierarchical byte-level language model that internalizes tokenization by learning to embed text from raw bytes through a multiscale, autoregressive U-Net architecture. This design avoids fixed token vocabularies like BPE and instead dynamically pools bytes into higher-order representations (words, word pairs, up to 4-word spans), enabling multi-stage prediction with varying granularities. Each stage compresses the sequence and predicts further ahead in time, combining coarse semantic abstraction with fine local detail via skip connections. Key insights:
ALE-Agent & ALE-Bench
Proposes a new benchmark for evaluating AI systems in score-based, long-horizon algorithmic contests. Unlike traditional coding benchmarks that emphasize pass/fail correctness, ALE-Bench is based on real tasks from the AtCoder Heuristic Contests (AHC), which focus on optimization problems with no known optimal solutions. The benchmark targets industrially relevant challenges such as routing, scheduling, and planning, encouraging iterative refinement and strategic problem-solving over hours or days. Key points:
Eliciting Reasoning with Cognitive Tools
Proposes a modular, tool-based approach to eliciting reasoning in LLMs, inspired by cognitive science. Rather than relying solely on RL or chain-of-thought prompting, the authors introduce a framework where the LLM calls self-contained "cognitive tools" to modularize and scaffold internal reasoning. These tools encapsulate operations like understanding questions, recalling analogous examples, examining answers, and backtracking. The system is implemented in an agentic tool-calling style, allowing LLMs to dynamically invoke tools during reasoning without extra fine-tuning. Highlights:
SHADE-Arena
This paper introduces SHADE-Arena, the first large-scale benchmark for evaluating whether LLM-based agents can subtly carry out harmful side objectives (sabotage) while avoiding detection by monitors. The dataset contains 17 complex task pairs, each with a benign main task and a related malicious side task, set in realistic, tool-using environments. Agents are evaluated on their ability to complete both tasks without raising suspicion from an LLM monitor. Key Findings:
Leaky Thoughts
This work explores how reasoning traces in large reasoning models (LRMs) leak private user data, despite being assumed internal and safe. The study finds that test-time compute methods, while improving task utility, significantly increase privacy risks by exposing sensitive information through verbose reasoning traces that are vulnerable to prompt injection and accidental output inclusion.
Advances in LLMs
This paper surveys recent advancements in LLMs focusing on reasoning, adaptability, efficiency, and ethics. It highlights techniques like CoT prompting, Instruction Tuning, RLHF, and multimodal learning, while also addressing challenges like bias, computational cost, and interpretability.
Reinforcement Pre-Training
This paper introduces Reinforcement Pre-Training (RPT), a new paradigm that bridges LLM pretraining and RL by reinterpreting next-token prediction as a reasoning task rewarded via verifiable correctness. Instead of relying on hand-curated annotations or costly human feedback, RPT applies RL on vast unannotated text corpora, assigning intrinsic rewards based on whether a predicted token matches the ground truth. This reframing supports general-purpose RL scaling and enhances both pretraining and fine-tuning efficacy.