Research Papers Prime Agent is an open harness for long-horizon coding agents built on the Recursive Language Model idea: a persistent IPython session does test-time computation, while histories, memories, skills and subagent specs carry over between runs.
FreeToken rethinks local inference around two realities of edge AI: agent workloads keep changing shape, and every machine's resource balance differs. It co-designs model layout, expert residency, CPU-GPU execution and memory management instead of committing to a fixed offloading strategy.
This survey decomposes a self-improving agent into a foundation model and an operational scaffold of prompts, memory, tools and control logic, then defines improvement as a self-induced update operator that converts experience into accumulated capability with minimal human input. It organizes the growing literature by update target and driving signal, from prompt and memory edits to weight-level self-modification.
This harness maintains an explicit task state outside the agent's execution context and updates it only with facts independently verified from the environment, using a Manage-Execute-Audit loop so mistaken self-assessments do not snowball across many steps.
ABot-World-0 is an action-conditioned video world model trained on multi-source data from AAA games, simulation engines and internet videos, controlled through raw keyboard input with reference-character memory for consistent third-person rollouts. The authors report streaming 720p at up to 16 FPS on one RTX 5090 with 1.2s action-to-first-frame latency, targeting real-time long-horizon closed-loop interaction.
SEED converts an agent's own completed on-policy trajectories into natural-language hindsight skills and distills the behavioral shift they induce back into the policy, producing a dense token-level training signal alongside outcome-based RL. The authors report gains in sample efficiency, final performance and generalization to unseen text- and vision-based agentic tasks.
After Meta's closed Muse demo showed what a single-person agent with lasting memory could look like, this report reconstructs how Muse is built from public sources, then ships nanoMuse as its GPL-3.0 open counterpart: one agent across the devices you own, sharing a single conversation over a relay anyone can self-host. Every action passes a Sentinel gate before it executes, memory is stored as plain files the owner can read, and the underlying model is the user's choice.
Raven argues that hand-crafted agent harnesses are too domain-coupled to scale with long-horizon, cross-domain workloads. It treats each model–harness pair as a composable unit of intelligence: a Host Agent decomposes goals and coordinates specialized sub-agents, a host archive and EverOS retain experience across tasks, and Skill Forge turns that experience into reusable procedures — with theory on expanding reliable task coverage under one resource budget.
Long-Horizon-Terminal-Bench tests agents on 46 multi-step terminal tasks across nine areas, from reproducing experiments to scientific computing. Each task is decomposed into fine-grained subtasks so agents earn partial credit for intermediate progress, and the authors report that frontier models still solve only a small fraction of runs.
Ouroboros is a self-developing coding-agent harness whose tools, prompts, context assembly and even core implementation improve through reviewed commits that become its later runtime, with two evolution modes: recursive free evolution and experience-driven core evolution. The authors also report a 161-day live deployment across seven human communication surfaces, arguing safety guardrails must stay authoritative while the agent rewrites its own code.
Iteratively editing an agent's harness (prompts, control flow, tooling, memory) can look like self-improvement while quietly overfitting the training tasks. RRSI regularizes both ends of the loop: the proposer works under a temporally annealed budget and is steered toward unexplored trajectories, while the selector uses a critic to screen benchmark-specific proposals and a pruner to drop edits that are too small, too expensive, or no longer useful. The authors report gains of up to 14.1 points on the evolved split and up to 4.7 points on five held-out benchmarks, with a harness that uses 30% fewer policy tokens.
AutoDesign treats multimodal conference-poster generation as a long-horizon agentic process: a meta-harness optimizer reads rollout feedback and rewrites the harness the code agent runs on. On the authors' 100-paper PosterBench it scores above Claude Design, the learned harness lifts seven different code-agent configurations, and a fully autonomous loop makes 253 tool calls in 40 minutes for under $3.
EvoOntology tackles the agent-data gap: agents can see column names and file paths through generic tools, but not what the data actually means. It wraps an ontology (schema, content, and tool layers) as an MCP server the agent can query at runtime, uses a builder agent to construct it autonomously, and keeps refining it with attribution-guided edits that are only accepted after a paired evaluation against the backbone. The authors report consistent gains over strong baselines and hand-built semantic layers across three data-agent benchmarks and four LLM backbones.
Apodex 1.1 targets what the authors call working capability: it scales up the diversity and verifiability of executable file, search and code environments, while training agents to decompose long-horizon tasks, delegate parallel work and integrate asynchronous results.
Gander treats video, speech and text as one continuous input stream instead of discrete turns: users can interrupt it at any time, and the model proactively gives intermediate feedback or asks follow-up questions, using a Cerebellum-Brain architecture to keep responses real-time.