6arXiv cs.CL (Computation and Language)·
SPyCE: Skill-Policy Co-evolution framework for multimodal agents via hierarchical skill libraries
Researchers introduce SPyCE (Skill-Policy Co-evolution), a training framework for multimodal agents that distills reasoning trajectories into a hierarchical skill library co-evolving with the policy during reinforcement learning. The library separates execution skills (local visual operations) from workflow skills (high-level tool orchestration priors), creating a closed loop where better policies yield better skills and vice versa. SPyCE outperforms both RL-based and memory-based baselines across eight benchmarks, suggesting joint skill-policy optimization as a viable paradigm for capable multimodal agents.
Related guides (3)
Related events (8)
SkillComposer: Structured skill composition for LLM agents via constrained autoregressive decoding
A new arXiv preprint introduces SkillComposer, a method that frames skill selection for LLM agents as a structured prediction problem — jointly deciding which skills to activate, how many, and in what order via a constrained autoregressive decoder over skill identifiers. The approach addresses a bottleneck in growing skill libraries where existing retrieval and full-context methods fail to capture the joint nature of skill composition. Evaluated on SkillsBench across two production-grade coding agents (GPT-5.2-Codex and Gemini-3-Pro-Preview), SkillComposer raises pass rates by +23.1 and +18.2 percentage points over no-skill baselines, matching gold-skill retrieval upper bounds at lower prompt-token cost.
SkillWeaver: Compositional Skill Routing for LLM Agents via Decompose-Retrieve-Compose
Researchers introduce SkillWeaver, a framework for compositional skill routing in LLM agents that decomposes complex queries into atomic sub-tasks, retrieves matching skills from a large library, and composes an executable DAG plan. The paper formalizes the Compositional Skill Routing problem and introduces CompSkillBench, a benchmark of 300 compositional queries over 2,209 real MCP server skills across 24 categories. A key finding is that task decomposition quality is the primary bottleneck, with standard LLM decomposition reaching only 34.2% category recall; the proposed Iterative Skill-Aware Decomposition (SAD) method improves decomposition accuracy from 51.0% to 67.7% in a single iteration. The framework also reduces context window consumption by over 99% compared to naive skill-stuffing approaches.
SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
SCOPE is a data-free self-play framework for training language models on open-ended tasks without external supervision or frontier-model judges. It co-evolves two policies—a Challenger that generates document-grounded tasks and a Solver that answers via multi-turn retrieval—using a frozen copy of the initial model as a self-judge that writes task-specific rubrics. Across three 7-8B models (Qwen2.5, Qwen3, OLMo-3), SCOPE achieves up to +10.4 points on eight open-ended benchmarks and +13.8 points on seven held-out short-form QA benchmarks, matching or exceeding GRPO trained on ~9K curated prompts. Ablations identify rubric generation quality as the primary bottleneck for self-judging.
SkillOpt: Systematic Text-Space Optimizer for Self-Evolving Agent Skills
SkillOpt introduces a principled optimization framework for agent skills, treating the skill document as an external trainable state analogous to model weights. A separate optimizer model converts scored rollouts into bounded edits (add/delete/replace) on a skill document, accepting only edits that improve held-out validation scores. Evaluated across six benchmarks, seven target models, and three execution harnesses (direct chat, Codex, Claude Code), SkillOpt achieves best or tied performance on all 52 evaluated cells, lifting GPT-5.5 no-skill accuracy by up to +24.8 points inside the Codex agentic loop. Optimized skill artifacts also transfer across model scales and execution environments without further optimization.
Skill-RM: A unified reward model framework treating evaluation as an agentic skill
Researchers from the Qwen team propose Skill-RM, a framework that reformulates reward modeling as the execution of a reusable 'Reward-Evaluation Skill,' enabling a single model to orchestrate heterogeneous evaluation criteria including rule-based verifiers, ground-truth references, and rubrics. By treating reward computation as a structured agentic task, Skill-RM dynamically selects and aggregates evidence per input rather than relying on static evaluation. Experiments on reward benchmarks and downstream tasks (best-of-N selection, RL) show consistent improvements over traditional judge baselines. The code is publicly released under the Qwen-Applications GitHub organization.
EvoPolicyGym benchmark evaluates autonomous policy evolution by LLM agents in RL environments
A new arXiv preprint introduces EvoPolicyGym, a benchmark for evaluating how LLM-based agents iteratively improve executable policies in compact interactive RL environments under a fixed interaction budget. The benchmark provides trajectory-level diagnostics beyond aggregate scores, distinguishing how agents allocate budget and convert feedback into parametric tuning. GPT-5.5 achieves the strongest aggregate rank score and top-two performance across all 16 environments. The work targets a gap in agent evaluation where iterative policy refinement is conflated with open-ended software engineering progress.
Scalable behaviour cloning for browser agents via skill distillation from human interaction traces
A new arXiv preprint proposes converting human browser interaction trajectories into compact natural-language skills that agents can retrieve and compose, arguing that the bottleneck for browser agents is decision-making under incomplete information rather than low-level operations. The approach organizes distilled skills into a skill graph to enable consolidation rather than unbounded accumulation. The work positions collective human browsing behavior as a scalable, under-exploited source of reusable agent priors, potentially reducing reliance on manually designed task demonstrations.
Systematic Study of Model-Generated Agent Skills Across the Full Skill Lifecycle
This paper presents a utility-grounded evaluation framework for model-generated agent skills, covering the full lifecycle of experience generation, skill extraction, and skill consumption across five agentic task domains. The authors find that while such skills are beneficial on average, they exhibit non-trivial negative transfer, and that skill utility is independent of model scale or baseline task strength. A key finding is that strong extractors are not necessarily strong consumers and vice versa. The work culminates in a 'meta-skill' that guides extraction toward utility-correlated features, consistently improving skill quality and reducing negative transfer.