AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
Large-Scale Study on Multi-Agent AI Systems Development
An empirical analysis of over 42,000 commits and 4,700 resolved issues across eight leading multi-agent frameworks (LangChain, CrewAI, AutoGen). Key findings: feature enhancements dominate at 40.8% of changes versus 27.4% bug fixes, bugs represent 22% of issues, with agent coordination challenges at 10%, and issue reporting surged notably beginning in 2023.
Learning Latent Action World Models In The Wild
Meta AI researchers address learning world models from in-the-wild videos without requiring explicit action labels, expanding beyond simple robotics simulations and video games to real-world video data with diverse embodiments and uncontrolled conditions.
Self-Evolving Search Agents Without Training Data
Dr. Zero introduces a framework for developing multi-turn search agents that improve themselves autonomously without labeled training data. A proposer generates diverse questions to train a solver initialized from the same base model, creating a self-evolution loop with automated curriculum difficulty scaling.
Unified Long-Term and Short-Term Memory for LLM Agents
AgeMem introduces a unified framework that integrates both long-term and short-term memory operations into an LLM agent’s decision-making policy. The system enables agents to autonomously determine what and when to store, retrieve, update, summarize, or discard information by exposing memory operations as tool-based actions.
Active Context Compression for LLM Agents
Focus introduces an agent-centered architecture that enables LLM agents to autonomously manage their own memory by deciding when to consolidate learnings into a persistent “Knowledge” block and actively prune raw interaction history. The design is inspired by the biological navigation patterns of Physarum polycephalum (slime mold).
Agent-as-a-Judge
This comprehensive survey traces the evolution from LLM-based evaluation to agentic evaluation approaches, establishing the first taxonomy for this paradigm shift. As evaluation tasks grow more intricate and specialized, traditional single-pass language model judges become insufficient.
Efficient Lifelong Memory for LLM Agents
SimpleMem introduces a memory framework built on semantic lossless compression that addresses the tension between maintaining comprehensive long-term memory and minimizing token overhead for LLM agents. The approach achieves a 26.4% F1 improvement over baselines while reducing token consumption by up to 30-fold during inference.
MemRL
MemRL enables LLM agents to improve continuously without retraining by separating a frozen model’s reasoning from an evolving memory system. A Two-Phase Retrieval mechanism filters candidates by semantic relevance, then ranks them using learned Q-values that improve through trial-and-error, outperforming existing methods on HLE, BigCodeBench, ALFWorld, and Lifelong Agent Bench.
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.
Adversarial Program Evolution with LLMs
Digital Red Queen (DRQ) introduces an algorithm where LLMs evolve assembly-like programs called “warriors” that compete for control of a virtual machine in the game of Core War. Rather than optimizing toward static objectives, DRQ embraces “Red Queen” dynamics where goals continually shift based on competition, demonstrating how adversarial self-play can drive the evolution of increasingly sophisticated programs.
Training AI Co-Scientists Using Rubric Rewards
This paper from Meta Superintelligence Labs presents a scalable method to train language models to generate better research plans without expensive human supervision or real-world execution. The approach automatically extracts research goals and goal-specific grading rubrics from scientific papers, then uses reinforcement learning with self-grading to improve plan generation.
Confucius Code Agent
Confucius Code Agent (CCA) is a software engineering agent designed to operate on large-scale codebases. Built on the Confucius SDK, it introduces a three-axis design philosophy separating Agent Experience (AX), User Experience (UX), and Developer Experience (DX) to enable robust multi-step reasoning and modular tool use.
SciSciGPT
SciSciGPT is an open-source AI collaborator that uses the science of science domain as a testbed for LLM-powered research tools. Its multi-agent architecture with five specialized modules automates complex research workflows and completes tasks in about 10% of the time required by experienced researchers while producing higher-quality outputs.
SWE-EVO
SWE-EVO introduces a benchmark for evaluating coding agents on long-horizon software evolution tasks that require multi-step modifications spanning an average of 21 files per task. The benchmark reveals significant limitations of current agents: GPT-5 with OpenHands achieves only 21% on SWE-EVO compared to 65% on SWE-Bench Verified, highlighting the gap between isolated bug fixes and realistic software development scenarios.
AI Agents for Coding in 2025
This study from UC San Diego and Cornell examines how experienced software developers (3+ years) actually use AI coding agents, through field observations (N=13) and surveys (N=99). The key finding: professional developers don’t “vibe code” - they carefully control agents through planning and supervision.
SAGA
SAGA (Scientific Autonomous Goal-evolving Agent) introduces a framework for automating objective function design in AI-driven scientific discovery. Rather than optimizing fixed objectives specified by scientists, SAGA dynamically reformulates research goals throughout the discovery process to avoid reward hacking issues.
Step-DeepResearch
Step-DeepResearch is a 32B parameter deep research agent that rivals OpenAI and Gemini DeepResearch through atomic capability training - decomposing research into planning, information gathering, cross-source verification, and report writing. Achieving 61.42 on Scale AI ResearchRubrics with a streamlined ReAct-style design, it outperforms larger models while being the most cost-effective deep research agent available.
AgentReuse
AgentReuse addresses latency bottlenecks in LLM-driven agents by caching and reusing plans for similar requests, observing that about 30% of agent requests are identical or similar. Using intent classification for semantic similarity rather than surface-level text comparison, the system achieves a 93% effective plan reuse rate and 93.12% latency reduction compared to systems without plan reuse.
LaMer
LaMer introduces a Meta-RL framework that enables LLM agents to actively explore and learn from environment feedback at test time. Unlike standard RL-trained agents that learn fixed policies and struggle with novel tasks, LaMer agents learn exploration strategies that transfer across environments.
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.
Self-Play SWE-RL
Self-Play SWE-RL (SSR) trains software engineering agents through self-play, requiring only access to sandboxed repositories with no human-labeled issues or tests. A single LLM learns to both inject and repair bugs of increasing complexity, achieving +10.4 points on SWE-bench Verified while consistently outperforming human-data baselines.
Empirical Study of Agent Developer Practices
This paper presents the first large-scale empirical study of LLM-based agent frameworks, analyzing 11,910 developer discussions across ten popular frameworks. The research identifies practical challenges developers face and evaluates how well current frameworks meet their needs.
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.
Detailed Balance in LLM Agents
Researchers establish the first macroscopic physical law in LLM generation dynamics by applying the least action principle to analyze LLM-agent behavior. They discover statistical evidence of detailed balance in state transitions, suggesting LLMs implicitly learn underlying potential functions rather than explicit rules.