AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
Discover and explore top AI papers with Claude Code or Codex
npx @dair-ai/mcp setup
ParamMem
Self-reflection enables language agents to iteratively refine solutions, but models tend to generate repetitive reflections that add noise instead of useful signal. ParamMem introduces a parametric memory module that encodes cross-sample reflection patterns into model parameters, enabling diverse reflection generation through temperature-controlled sampling.
Reaching Agreement Among LLM Agents
This paper introduces Aegean, a consensus protocol that frames multi-agent refinement as a distributed consensus problem. Rather than static heuristic workflows with fixed loop limits, Aegean enables early termination when sufficient agents converge, achieving 1.2-20x latency reduction across four mathematical reasoning benchmarks while maintaining answer quality within 2.5%. The consensus-aware serving engine performs incremental quorum detection across concurrent agent executions, cutting wasted compute on stragglers.
Phi-4-reasoning-vision-15B
Microsoft presents Phi-4-reasoning-vision-15B, a compact open-weight multimodal reasoning model that combines visual understanding with structured reasoning capabilities. Trained on just 200 billion tokens of multimodal data, the model excels at math and science reasoning and UI comprehension while requiring significantly less compute than comparable open-weight VLMs. The key insight is that systematic filtering, error correction, and synthetic augmentation remain the primary levers for model performance, pushing the Pareto frontier of the accuracy-compute tradeoff.
Deep-Thinking Tokens
Google researchers challenge the assumption that longer outputs indicate better reasoning. They introduce deep-thinking tokens, a metric that identifies tokens where internal model predictions shift significantly across layers before stabilizing. Unlike raw token count, which negatively correlates with accuracy (r = -0.59), the deep-thinking ratio shows a robust positive correlation (r = 0.683).
Discovering Multi-Agent Learning Algorithms with LLMs
Google DeepMind uses AlphaEvolve, an evolutionary coding agent powered by LLMs, to automatically discover new multi-agent learning algorithms for imperfect-information games. Rather than relying on manual algorithm design, the system navigates vast algorithmic design spaces and discovers non-intuitive mechanisms that outperform state-of-the-art baselines.
CoT Faithfulness via REMUL
Researchers propose REMUL, a training approach for making chain-of-thought reasoning more faithful and monitorable. A speaker model generates reasoning traces that multiple listener models attempt to follow and complete, using RL to reward reasoning that is understandable to other models. Tested across BIG-Bench Extra Hard, MuSR, ZebraLogicBench, and FOLIO, REMUL improves three faithfulness metrics while also boosting overall accuracy, producing shorter and more direct reasoning chains.
CogRouter
CogRouter enables adaptive reasoning depth for LLM agents by dynamically selecting from four hierarchical cognitive levels at each step, from instinctive responses to strategic planning. Using confidence-aware advantage reweighting during training, Qwen2.5-7B with CogRouter achieves 82.3% success rate on agentic benchmarks, substantially outperforming larger models while consuming fewer tokens by skipping heavy reasoning on routine steps.
Team of Thoughts
Team of Thoughts presents a multi-agent framework for efficient test-time scaling through orchestrated tool calling. The system uses an orchestrator tool design where agents with different capabilities are coordinated by a calibrated orchestrator. With self-assessment for tool agents and orchestrator calibration for identifying superior coordination models, Team of Thoughts achieves 96.67% on AIME24 and 72.53% on LiveCodeBench, substantially exceeding homogeneous baselines.
InftyThink+
InftyThink+ is an end-to-end RL framework for infinite-horizon reasoning that optimizes the entire iterative reasoning trajectory. Standard long chain-of-thought suffers from quadratic cost, context length limits, and lost-in-the-middle degradation. InftyThink+ addresses all three by letting models autonomously decide when to summarize, what to preserve, and how to resume, trained through trajectory-level reinforcement learning.
AgentArk
AgentArk distills multi-agent debate dynamics into a single LLM, transferring the reasoning and self-correction abilities of multi-agent systems into one model at training time. Three hierarchical distillation strategies (reasoning-enhanced SFT, trajectory-based augmentation, and process-aware distillation with a process reward model) yield an average 4.8% improvement over single-agent baselines across math and reasoning benchmarks, approaching full multi-agent performance at a fraction of the inference cost. Cross-family distillation (e.g., Qwen3-32B to LLaMA-3-8B) produces the largest gains, suggesting heterogeneous architectures benefit most from transferred reasoning signals.
Semi-Autonomous Mathematics Discovery with Gemini
This paper from Google DeepMind presents a case study in semi-autonomous mathematics discovery using Aletheia, a specialized math research agent built on Gemini Deep Think. The team systematically evaluated 700 open conjectures from Bloom’s Erdos Problems database, combining AI-driven natural language verification with human expert evaluation, and addressed 13 previously open problems.
Accelerating Scientific Research with Gemini
A collection of case studies from Google Research showing how researchers used Gemini Deep Think to solve open problems, refute conjectures, and generate new proofs across theoretical computer science, information theory, cryptography, optimization, economics, and physics. The paper extracts a practical playbook of recurring techniques, including iterative refinement, cross-disciplinary knowledge transfer, counterexample search, and neuro-symbolic verification loops where the model autonomously writes and executes code to validate derivations. Notable results include identifying a fatal flaw in a cryptography preprint on SNARGs, resolving the Courtade-Kumar conjecture in information theory, and proving that the simplex is optimal for Euclidean Steiner trees.
Reinforcement Learning via Self-Distillation
This paper introduces Self-Distillation Policy Optimization (SDPO), an on-policy RL algorithm that converts rich textual feedback from verifiable environments into dense credit assignment without requiring an external teacher model. SDPO uses the current model conditioned on feedback as a “self-teacher” to retrospectively identify mistakes in its own rollouts, substantially outperforming GRPO across scientific reasoning, tool use, and competitive programming.
TTT-Discover: Learning to Discover at Test Time
TTT-Discover introduces test-time training for scientific discovery, performing reinforcement learning at test time so the LLM can continue to train with experience specific to the test problem. Unlike prior work like AlphaEvolve that prompts a frozen LLM, this approach enables the model itself to improve while attempting to solve hard problems.
Reasoning Models Generate Societies of Thought
This paper reveals that enhanced reasoning in models like DeepSeek-R1 and QwQ-32B emerges not from extended computation alone, but from simulating multi-agent-like interactions - a “society of thought” - enabling diversification and debate among internal cognitive perspectives with distinct personality traits and domain expertise.
Task-Decoupled Planning for Long-Horizon Agents
Task-Decoupled Planning (TDP) is a training-free framework that restructures agent planning by decomposing tasks into a directed acyclic graph of sub-goals using three components: Supervisor, Planner, and Executor. By isolating reasoning to individual subtasks through scoped contexts, TDP prevents error cascading and reduces token consumption by up to 82% while outperforming baselines on TravelPlanner, ScienceWorld, and HotpotQA.
Recursive Language Models
Recursive Language Models (RLMs) are a general inference strategy that allows LLMs to process arbitrarily long prompts by treating them as part of an external environment. Rather than feeding long contexts directly into the model, RLMs load the prompt as a variable in a Python REPL and let the LLM programmatically examine, decompose, and recursively call itself over snippets.
Nemotron-Cascade
Nemotron-Cascade introduces cascaded domain-wise reinforcement learning (Cascade RL) to build general-purpose reasoning models capable of operating in both instruct and deep thinking modes. Rather than blending heterogeneous prompts from different domains, Cascade RL orchestrates sequential, domain-wise RL stages that reduce engineering complexity while delivering state-of-the-art performance.
Universal Reasoning Model
This paper investigates why universal transformers excel at complex reasoning tasks like ARC-AGI. The key finding: performance gains come primarily from recurrent inductive bias and strong nonlinear components rather than elaborate architectural designs.
MACI
This paper argues that LLMs are not fundamentally limited as pattern matchers - the real bottleneck is the lack of a System-2 coordination layer. The authors propose MACI, an architecture implementing three mechanisms: baiting (behavior-modulated debate), filtering (Socratic judging), and persistence (transactional memory) to enable goal-directed reasoning on top of LLM substrates.
Monitoring Monitorability
OpenAI introduces a framework for measuring how well we can detect misbehavior in AI systems by monitoring their chain-of-thought reasoning. The paper proposes three evaluation archetypes and a new metric (g-mean2) to track monitorability across different models and training regimes.
Epistemia
This paper argues that LLMs are not epistemic agents but stochastic pattern-completion systems. By mapping human and artificial epistemic pipelines, the authors identify seven fundamental fault lines where human and machine judgment diverge, despite producing superficially similar outputs.
JustRL
JustRL challenges the assumption that complex RL pipelines are necessary for training small language models. Using single-stage training with fixed hyperparameters, the authors achieve state-of-the-art math reasoning performance on two 1.5B models while using 2x less compute than sophisticated multi-stage approaches.
Sophia
Sophia introduces System 3, a meta-layer beyond traditional dual-process theory that enables LLM agents to maintain persistent identity and align short-term actions with long-term goals. The framework achieves 80% reduction in reasoning steps for recurring operations and 40% performance improvement on high-complexity tasks.