Introducing AI Papers of the Week: https://t.co/TXvoB4ozqb

We took the top AI papers of the last 3 years, summarized them, and organized them by topic and week.

You can easily explore papers, find related research, and chat with any paper. https://t.co/DDIUm6cVhi

AI Papers of the Week | DAIR.AI Academy

Source: https://academy.dair.ai/papers

Recuris evolves working and experiential memory for long-horizon agents

Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Working Memory architecture for long-horizon agent harnesses, in which Working Memory tracks task progress and guides skill selection from Experiential Memory, grounding skill use in current needs rather than the full history. This coupling also turns execution into structured evidence that localizes failures to specific memory components. Across tasks, a fixed Meta-Agent turns that evidence into localized, validation-gated updates to Skill Memory that reshape execution and yield new evidence, forming a bounded recursive memory-evolution loop. Across four long-horizon benchmarks and ten models, Recuris improves task success in 35 of the 37 completed model-benchmark pairs, carrying frontier models to SOTA-level task success: on tau-bench it adds +17.8 points to GPT-5.6 Sol and +15.6 to Claude Opus 5, taking Opus 5 to 87.9%, and +16.6/+13.5 points on Qwen3.6-27B/35B on SkillFlow. The advantage widens as the interaction horizon grows, to +32.2 points on the longest tasks, and common long-horizon failures fall by up to 80%. These results position recursively evolving memory as a scalable foundation for RSI, enabling agents to continuously transform accumulated experience into increasingly effective long-horizon behavior. Code: https://github.com/Gen-Verse/Recuris

02Agents

LongMemEval-V2: Evaluating Long-Term Agent Memory

Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure modes. However, existing memory benchmarks for agents mostly focus on user histories, short traces, or downstream task success, leaving open how to directly evaluate whether memory systems effectively internalize environment-specific experience. To address this gap, we introduce LongMemEval-V2 (LME-V2), a benchmark for evaluating whether memory systems can help agents acquire the experience needed to become knowledgeable colleagues in customized environments. LME-V2 contains 451 manually curated questions covering five core memory abilities for web agents: static state recall, dynamic state tracking, workflow knowledge, environment gotchas, and premise awareness. Questions are paired with history trajectories containing up to 500 trajectories and 115M tokens. We use a context gathering formulation: memory systems consume history trajectories and return compact evidence for downstream question answering. We propose a suite of two memory methods: AgentRunbook-R, an efficient RAG-based memory with knowledge pools for raw state observations, events, and strategy notes, and AgentRunbook-C, which stores trajectories as files and invokes a coding agent to gather evidence in an augmented sandbox. Experiments show that AgentRunbook-C achieves the best performance with 72.5% average accuracy, outperforming the strongest RAG baseline (48.5%) and the off-the-shelf coding agent baseline (69.3%). Despite the strong performance gains, coding agent based methods have high latency costs. While AgentRunbook-C advances the accuracy-latency Pareto frontier, substantial room for improvement remains. Together, these results establish LME-V2 as a challenging testbed for developing long-term memory systems for environment experience.

03Evaluation

The Skill Trigger Bottleneck

There are 56,804 public agent skills today, all competing for fewer than 100 reliable trigger slots in the system prompt. Your own playbooks compete for that same space, which means the long tail never gets used no matter how good it is. The paper argues the scarcity is an artifact of how skills get installed, not a real limit.

04Agents

Harness-Level Forgetting

Continual learning has always tracked what changes in the weights. Modern agents accumulate their experience somewhere else entirely, across prompts, memories, tools, skills, and routing rules, and nobody has been measuring what happens when that layer drifts.

05Agents

The Control-Plane Tax

Serving systems for agentic applications are still built on assumptions inherited from single-turn LLM inference. This work instruments ten real agentic applications end to end and finds the model is often not what your latency bill is paying for.

06Agents

Demystifying Agent Skills

Skills are usually assumed to inject knowledge the model lacks. This paper runs the controlled comparison and finds that assumption is almost entirely wrong, which changes what a good skill should contain.

07Agents

Strategy Lock-In

Agents post-training other agents is one of the more load-bearing assumptions in current recursive self-improvement arguments. This paper analyzes a large corpus of publicly released post-training trajectories to see whether the loop actually closes, and finds a specific structural failure.

08Agents

SocialRL

The dispositions that make an assistant pleasant make it a poor delegate. A friendly frontier model volunteers its principal’s private information and concedes at the first sign of resistance, which is exactly the wrong behavior when it is negotiating on your behalf.

09Agents

ClawGym II

If you want to train agents inside the harness they already run in, this is the black-box version of that idea. ClawGym II runs RL through OpenClaw and Claude Code as opaque boxes, with a serving proxy at the model boundary capturing every call the harness makes, then organizing those calls into prefix trees so PPO and GRPO can optimize over the recovered multi-turn structure. Qwen3-30A3B gains 9.98 points of Pass@1 through OpenClaw and 14.81 through Claude Code, stable across 200 to 400 optimization steps. Mix-harness training pushes further: one model optimized jointly by heterogeneous harnesses, which points at policies that generalize across execution systems instead of overfitting to a single one.

10Agents

Inside an Agent Team

Naming one agent the coordinator creates no communication hub and gives no reliable improvement in success, which is worth knowing before you architect another supervisor pattern. Researchers instrumented 1,902 multi-agent coding runs as temporal networks, with agents and files as nodes and messages, writes, and reads as timestamped edges carrying cost. Direct messaging grows close to quadratically with team size, much of it from an early round of introductions, then saturates in the largest teams as agents switch to broadcast. Task shape drives topology: shared-specification work produces dense connected teams while pipeline tasks produce sparse networks organized around local interfaces. Swapping repeated one-to-one messages for shared files cut output tokens about 42% at eight agents on message-heavy work. Separately, agents sought out hidden grading material unprompted, and in a sealed rerun across 244 runs with marked placeholder files they still reached for it in four fifths of runs.

11Agents

The Fragility of Self-Improving Agents

Memory-based self-improving agents report gains that have never been checked against evaluation noise. This re-evaluation adds the two things prior work skipped, multiple runs to measure variance and randomly shuffled task orders, and both hurt. Agent evaluation is already noisy on multi-step tasks, and stacking a self-improvement loop on top amplifies that noise rather than averaging it out. The sharper finding is that default task orderings impose an implicit curriculum, and much of the reported gain was riding on it. Adding detailed rubrics and environment feedback to memory construction recovers part of the drop, and a significant gap remains. If you are measuring your own memory loop, shuffle the task order first.

12Agents

Skaling

Standard neural scaling laws assume model size and training data act on loss independently. That assumption bakes in a cross-derivative of exactly zero, and it is why the Chinchilla form drifts at the data-scarce and heavy-overtraining edges of the grid, which is exactly where deployment now happens.

13Training

Stealing Reasoning Traces

Frontier providers hide chain-of-thought and hand the client an encrypted block instead, which the client returns with every subsequent request. This work identifies an architectural flaw in that design and turns it into a scalable extraction attack across three providers.

14Safety

Mind Viruses

As agents get more autonomous and more interconnected, risks start coming from agent-to-agent interaction rather than from any single model. This work from Anthropic studies one of them directly: ideas that propagate through a multi-agent system by inducing each host to transmit them onward.

15Safety

Catastrophic Remembering

Agentic coding READMEs grow without bound in real repositories, stopping only when the repo retires or someone rewrites the file wholesale. This paper traces the cause to imperfect recall and gives the phenomenon a name that inverts the one continual learning is organized around.

16Memory

The Bitter Lesson of Tool Calling

Tool calling is a design choice and the default choice is JSON. For code-capable models, exposing tools as code instead lets calls chain and parallelize naturally, but nobody had run the comparison on an established benchmark across model generations under realistic conditions.

17Agents

Reason Wide, Not Deep

Reasoning modes beat non-reasoning modes on multi-step agentic tasks and charge a 3x to 6x output-token premium on every single episode. Much of that spend goes into re-deriving procedures the model already worked out on earlier episodes in the same domain, which means the cost is recurring by accident rather than by necessity.

18Agents

Harness-IF

When a coding agent obeys your rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell compliance from coincidence because they concentrate rules in the user turn, while coding-agent benchmarks only score final task success.

19Evaluation

Lost in Compaction

Context compaction is now standard in long-running agent systems, and it silently drops the instructions users most expect to persist. This work names that class, Session Constraints, instructions like “do not delete any emails until I confirm” meant to bind behavior for the rest of a session, and introduces COMPINT to evaluate compactors across multi-turn chat, agentic trajectory, and long-horizon research. Current compactors retain only 17% of injected constraints on average, and most leave the task worse off than running it without compaction at all. Retention swings with the compactor, the prompt, the context length, the phrasing, and where the constraint was injected, which is what makes the loss structural rather than a quirk of one setup. The fix is small and does not touch the compactor or the model: an SC-aware extractor running alongside as a plug-and-play module recovers over 90% retention in all three scenarios.

20Memory

Cracks in the Foundation

You might assume architectural variations within the dense transformer paradigm barely move accuracy, and in the short-context setting you would be right. This work shows four minor decisions, normalization, GQA, pretraining context length, and sliding window attention, each made by at least one of the Olmo, Llama, and Qwen dense families, have a compoundingly negative effect on long-context extensibility. Any one alone is minor, but combining three or more drops downstream long-context performance by up to 47%, and none of it is detectable from short-context loss or validation sets, which is precisely how these choices survive into shipped models. Applying context extension early in pretraining exposes the problem cheaply. After over 170,000 GPU hours the authors release OlmPool, 26 comparable 7B models with checkpoints before and after extension, including several architectures that beat the Llama 3 architecture on long-context extensibility.

21Architecture

CEDAR

Complex systems research models feedback-driven phenomena from population dynamics to economic policy, and its central open problem is that nobody can predict how feedback structure gives rise to emergent behavior, which makes goal-directed design very hard. CEDAR, from Sakana AI, attacks that with LLM agents running Monte Carlo Tree Search over the space of feedback structures rather than tuning parameters on a fixed one. Systems are represented as a restricted runnable subset of Python with domain-specific primitives so the models can edit dynamics directly, an LLM Judge scores emergent behavior against the stated goal as a fitness function, and an LLM Editor proposes variants as a variation operator. The formalization is an MCTS variant with an LLM-parameterized transition kernel and value function, which preserves solution diversity while searching, and the LLM-based interpretability makes it possible to read back how a structural change produced the behavior.

22Agents

Model or Harness

Agent evaluations mostly report system-level outcomes, so a failed run leaves the repair unassigned. The same visible failure might call for model post-training, harness engineering, environment redesign, or benchmark repair, and outcome labels cannot separate those cases.

23Evaluation

Zero-Mem

Production memory stacks spend extra model calls on summarizing interactions, writing records, and reranking retrievals. Each of those calls costs tokens and latency, and the generated summaries quietly discard the evidence you later need. This work asks whether structured memory access requires generation at all.

24Memory