AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
The Verification Horizon
Reinforcement learning for coding agents lives or dies on the reward signal, and this Qwen work argues there is no silver bullet. As policy capability grows, any fixed reward function eventually gets gamed, so verification has to co-evolve with the generator it scores. ---
Paper Assistant Tool
AI is accelerating how fast papers get written, but peer review is still bottlenecked on human throughput, with combined submissions to the big ML conferences projected to top 73,000 this year. Google’s Paper Assistant Tool is an agentic framework built to do deep scientific review and verification at that scale. ---
Generative Skill Composition
Coding agents accumulate large skill libraries, and picking the right skills for a task has become the bottleneck. The usual options either dump the whole collection into context or retrieve skills with embeddings and rerankers, and both treat selection as a ranking problem rather than a joint plan. ---
AutoMem
Memory for LLM agents is usually a fixed module bolted onto the model, but knowing what to encode, when to retrieve, and how to organize notes is itself a skill. AutoMem, from Stanford, treats memory management as a trainable cognitive ability, a capacity cognitive science calls metamemory. ---
RLMF
LLMs routinely hallucinate with high confidence, miss their own knowledge boundaries, and misreport uncertainty, and most fixes bolt calibration on from the outside. RLMF, a Google and Yale collaboration, instead turns the model’s own metacognition into the training signal. ---
ASPIRE
ASPIRE reframes robot programming as continual, code-as-policy learning that compounds experience instead of discarding it. The system runs an open-ended loop with a closed-loop execution engine that exposes fine-grained multimodal traces, a skill library that distills validated fixes into transferable knowledge, and an evolutionary search over task sequences and control programs. It surpasses prior methods by up to 77% on perturbed manipulation and enables zero-shot generalization to unseen long-horizon tasks, with early evidence of sim-to-real transfer across different embodiments. ---
HORIZON
HORIZON treats hardware design as repository-level code evolution, compiling a Markdown harness into a project pack with domain knowledge, an executable evaluator, an acceptance predicate, and a git and runtime policy. A hands-free agent loop then evolves an isolated git worktree, using repository operations for state management, tracing, and replay. Across ChipBench, RTLLM, Verilog-Eval, and nine CVDP categories it reaches full benchmark completion with a completely hands-free loop, extending repository-scale self-evolution from EDA software to hardware artifacts themselves. ---
Reasoning Quality Emerges Early
Curating reasoning data is expensive because scoring a trace usually means reading it to the end, but this UCLA work shows the quality of a trace is largely decided in its opening tokens. A short prefix predicts whole-trace quality well enough to rank and filter on, and difficulty can be detected from the loss of the first 100 tokens at a perturbed checkpoint. That turns curation into a cheap early-stopping problem, outperforming baselines while being far more token efficient at building SFT data for reasoning models.
Sakana Fugu
Frontier LLMs keep advancing, and different providers are increasingly specializing in distinct domains, which raises a natural next objective: how do you combine those individual specializations into one collectively intelligent system? Sakana Fugu answers with a family of orchestrator models that are themselves language models trained to read a user query and dynamically devise the agentic scaffold needed to solve it.
Agent-Native Memory
Memory for LLM agents has quietly grown from a retrieval add-on into a full data system, with persistent storage, retrieval, update, consolidation, and lifecycle governance running throughout an agent's execution. Yet most evaluations still score memory only through end-to-end task metrics like F1 and BLEU, treating the whole stack as a black box. This paper studies agent memory from a data management perspective and asks what we are actually missing when we measure it that way.
Autodata
Building synthetic training data has mostly stayed a fixed pipeline that you hand-tune once and then freeze. Autodata rethinks that by casting an AI agent as a data scientist that builds high-quality training and evaluation data, then meta-optimizes that agent so it learns to create even stronger data over time.
Critique of the Agent Model
The word agent now covers everything from a for-loop with tool calls to speculative machine superintelligence, which makes it nearly useless as a technical term. This position paper from Eric Xing and collaborators tries to fix that by asking what an agent actually is and what agency consists of, drawing on Descartes and on science-fiction portrayals of autonomous beings to ground the discussion.
Agent-as-a-Router
Most users now have access to many LLMs that each excel in different domains, so routing each task to the right model matters for both quality and cost. Existing routers treat this as a static, one-off classification problem, and this paper shows that framing is exactly what holds them back.
Agent Communication Protocols
As multi-agent systems try to move past the limits of standalone agents, communication becomes the load-bearing infrastructure, and the protocol landscape for it is a fragmented mess. This study builds a technical taxonomy to classify and compare LLM agent communication protocols and to make the interoperability problem legible.
A Pinch of Human Data
Self-play reinforcement learning can train driving policies with no human data at all, swapping expensive human demonstrations for cheap large-scale simulation. The catch is that pure self-play tends to discover effective but alien driving conventions that real people cannot work with, and the usual fixes lean on brittle reward engineering and domain randomization.
Skill-MAS
Automatic generation of multi-agent systems is stuck between inference-time methods that reuse frozen frontier models but never learn, and training-time methods that internalize experience through gradient updates but are capped by the weaker models small enough to fine-tune. Skill-MAS proposes a third path that treats high-level orchestration as an evolvable Meta-Skill, decoupling experience retention from weight updates so frontier models keep getting better at orchestration without any gradient steps. Across four complex benchmarks and four distinct LLMs it delivers strong, transferable gains at a favorable cost-performance trade-off.
Reliability without Validity
LLM-as-a-Judge is the default way to evaluate language models, but validating those judges with exact-match agreement never corrects for chance and systematically overstates how good they are. In the largest audit to date, spanning 21 judges from nine providers across MT-Bench, JudgeBench, and RewardBench over 118 runs and roughly 541,000 judgments, the gap between raw agreement and chance-corrected Cohen's kappa runs 33 to 41 percentage points, rankings shift by up to 14 positions across benchmarks, and high test-retest reliability coexists with severe position bias. The authors distill their findings into a Minimum Viable Validation Protocol so teams can stress-test judges before trusting them.
NatureBench
Can coding agents move past reproduction toward actual discovery on real scientific problems? NatureBench distills 90 cross-discipline tasks from peer-reviewed Nature-family papers and runs them in NatureGym, an automated pipeline that builds a standardized containerized environment per task to fix the environment-fragmentation problem. Under a strict web-search-disabled protocol, the strongest of ten frontier agent configurations beats published SOTA on only 17.8% of tasks, and analysis shows agents win mainly by translating problems into familiar supervised prediction rather than through genuine scientific invention.
SpatialClaw
Spatial reasoning over 3D and 4D scenes is still where general vision-language models break down, because they emit a text answer directly rather than measuring anything. From NVIDIA, SpatialClaw is a training-free framework that rethinks the action interface and lets a VLM-backed agent reason through code instead. The agent writes one Python cell per step into a persistent Jupyter kernel preloaded with perception primitives and scientific libraries, then inspects intermediate results and revises its strategy across steps.
Compositional Skill Routing
Real tasks rarely map to a single skill. They usually need several skills composed together, yet most skill routing still treats the problem as picking one tool from a library. This work formalizes Compositional Skill Routing, where an agent must select and sequence multiple reusable skills from large libraries to satisfy a complex query, and introduces SkillWeaver, a decompose, retrieve, and compose pipeline built around it.
PreAct
Computer-using agents drive real software through the screen, but they solve every task from scratch. Ask one to repeat a task and it re-reads the screen and re-reasons every tap, paying the full cost again. PreAct fixes this by compiling the first successful run into a small state-machine program, where states check the screen and transitions act, then replaying that program on later runs instead of invoking the agent.
Can LLM Agents Infer World Models?
Can an LLM agent actually build a model of an environment it cannot see? This work makes that question gradeable through agentic automata learning. An agent has to uncover a hidden deterministic finite automaton by interacting with an oracle through two interfaces, membership queries that ask whether a string belongs to the target language, and equivalence queries that ask whether a proposed automaton is correct, which yields a clean, scalable testbed for interactive discovery.
From Trainee to Trainer
Who should design the training environment for an RL agent, the practitioner or the policy itself? RL pipelines for LLMs usually rely on manually redesigned environments between stages, with practitioners guessing which configuration will best improve the current policy. This paper hands that job to the model, proposing an LLM-as-Environment-Engineer framework where the policy diagnoses its own weaknesses and proposes the next environment to train on.
OpenClaw-Skill
Equipping LLM agents with effective skills is most of the battle in real systems, yet most skill-induction work distills one trajectory at a time, which produces narrow, brittle skills. OpenClaw-Skill introduces Collective Skill Tree Search, a tree-search-based skill construction framework that builds a structured, diverse, and generalizable tree of skills, then trains agents to actually use what it builds.