PIMiner uses a transferable strategy library to push prompt injection ASR to 76–87% at ~$20 query cost; Agent Skills Can Be Harmful finds that seemingly relevant skills are more likely to derail tasks than obviously unrelated ones, with excessive procedures accounting for 62.6% of efficiency degradation; Order 66 scenario analysis uses a compositional threat model to show that dormant implants, post-hoc memory poisoning, and peer-to-peer diffusion are individually non-fatal but can sustain self-propagation when combined
Vercel ships eve, a filesystem-first TypeScript agent framework tightly coupled with its AI Gateway/Sandboxes; Prime Intellect's Prime Agent treats the entire conversation context as program variables with a self-modifying Continual Harness; aden-hive's Hive replaces pre-compiled execution graphs with 'clone the Queen'; HKUDS's nanobot hits 47k stars in six months with its v0.3.0 Agency Release. No major version bumps on the watchlist today.
Mastra 1.59.0 highlights: (1) CostGuardProcessor renamed and upgraded to TokenCostControl, now supporting user/organization/session tiered budgets with warnAtPercent alerts; (2) Breaking: Factory's autoRunEnabled now defaults to false — rule-suggested executions enter a proposed state pending approval; (3) New listActiveThreadRuns() for low-cost querying of in-progress runs, enabling status-polling UIs.
Vals AI closes a $40M Series A led by Andreessen Horowitz at a $400M valuation. The round signals that VCs are starting to treat 'independent AI evaluation' as essential trust-layer infrastructure for the AI economy — not a nice-to-have leaderboard site.
DeepSeek V4-Pro peak Output jumped from $0.87 to $3.96/1M tokens (↑355%), V4-Flash from $0.28 to $1.32 (↑371%), effective 2026-08-16 16:00 UTC. Off-peak rates are half of peak (peak hours: 01:00-04:00 and 06:00-10:00 UTC). Post-hike prices still undercut GPT-5.6 and Claude, but the low-cost moat has narrowed significantly.
AgenticSeek (a 26K-star local AI Agent project on GitHub) has its backend bound to 0.0.0.0:7777 by default with CORS wide open. Anyone who can reach that port can send unauthenticated requests to the /query endpoint, which drives the Agent's BashInterpreter to run arbitrary commands via shell=True, safety=False — full host-level RCE (CVE-2026-72776, CVSS 9.3). The project has patched the issue (defaulting to loopback binding and allowlist CORS), but unpatched deployments remain exposed.
GitHub account zellkernel submitted PRs to 23 AI/MCP/dev-tool projects within 74 minutes, injecting a MCP server called productivity-suite into their config files. The server initially offers harmless text formatting and summarization, but an internal counter flips tools/list and prompts/get into malicious instructions after three tool calls — directing the Agent to search for SSH keys, AWS credentials, shell history, and Kubernetes configs while hiding the activity from the user. All 23 PRs remain unmerged (19 closed, 4 open), but the malicious endpoint is still live. Defense: treat any change to an approved MCP server's tool definitions as a security event requiring re-approval, and block the known endpoints.
pbx-mcp is an MCP server that wraps Asterisk (AMI) and FreeSWITCH (ESL) behind one set of MCP tools. Install: npx -y pbx-mcp. It solves the problem of memorizing two command sets when operating two PBX systems, and prevents Agents from accidentally running state-changing commands.
SkillEvo replaces single-turn QA evaluation with multi-turn interaction feedback so skill evolution doesn't stall after the first round, outperforming self-reflection by 23 points; SkillShapley brings Shapley values to skill step attribution — 99 evaluations approximate the exact ranking, revealing that 'decision-bridging steps' are the high-value ones; MindMemOS unifies memory management with an entity-property-time structure, hitting 94% on LOCOMO and lifting SpreadsheetBench success rate by 9.2 percentage points through skill evolution
Harness-IF reveals Coding Agent instruction following is overestimated by 3.6-7.4 pp because things the model would do anyway are counted as compliance; SHE decomposes the harness into four safety components and auto-evolves from trajectory failures, cutting ASR by 3.1x while improving correctness; SBCO uses a decomposed verifier bank with text gradients for harness self-improvement, matching Gödel Machine at 4-5.5x lower compute on planning tasks
EvoGraph-Mem uses a failure-aware editable graph to let agent memory self-correct, preventing stale insights from poisoning decisions; MAP-Graph turns provenance tracking from post-hoc audit into real-time access control, achieving 95% success across 2,700 synthetic tasks; MaSRead shows multi-agent KV cache sharing is possible but requires content-addressed reading instead of positional addressing
Tool interface design boosts coding agent consistency by 4.7x while halving token usage; memory distillation lifts a 4B model's AppWorld accuracy by 27.2 percentage points to near-frontier level; institutional design experiments show that identical safety rules paired with different enforcement mechanisms yield violation rates ranging from 0% to 23%
Muscle Memory proposes 'compiled memory' over retrieval-based memory, winning 88.9% of personalization matchups across 90 scenarios; MoRSE uses role-subtask conditioned LoRA experts to significantly outperform prompt-only role differentiation in code generation; ASCon builds a unified failure attribution model, improving by 5.83%, 10.63%, and 14.73% across three attribution targets
Evo-Bench benchmarks nine models on self-improving harnesses — GPT-5.6 Sol tops at +16.6 but Office tasks barely move; MEGA uses a three-layer Wisdom Graph to make agent optimization infrastructure self-evolving, merging knowledge accumulation with optimization; SHE decomposes harnesses into four evolvable components that learn safety boundaries from failure trajectories, cutting ASR by 3.1x with cross-model transferability
OneDayAgent's decompose-remember-verify harness hits 0.821 new SOTA on AgentIF-OneDay and works unchanged across five backends; The Horizon Gap surveys 1,547 papers to find that six categories of long-horizon failure share a single structural pattern — outcome-only signals degrade as step count grows, driving the field toward denser process signals; Evo-Bench is the first benchmark for harness self-evolution — GPT-5.6 Sol peaks at +16.6 absolute gain, but Office tasks still need hand-crafted workflows
Memory Reward Inflation finds that self-improving agents' memory rewards self-inflate — wrong experiences grow more confident over time; LUCID boosts accuracy from 54.0% to 56.9% on BIRD. RoMeRL compresses memory state space with fixed-dimension semantic coordinates, cutting Cold-Q ratio by 80% and LLM calls by 21.1%. ToolLIFT abstracts tool trajectories into function-level workflow graphs, consistently outperforming existing methods on three OOD benchmarks
ToolLIFT lifts tool trajectories to function-level workflow graphs and consistently beats SOTA on three OOD benchmarks; SkillTV-Bench uses 681 cases to show skill-aware judge skills boost agent evaluation accuracy by 14.8pp; TRIO-20's prespecified equivalence study finds zero unauthorized calls from GPT-5.6 across 840 trajectories, but higher reasoning effort increases rule-probing rate by 14.3pp
VerMem's seven atomic memory operations plus dual verifiers lead all baselines by 5-8 points across five benchmarks; SafeCommit cuts unsafe action rate from 41.2% to 2.6% while maintaining 97.4% task completion; ToolLIFT abstracts tool trajectories into function-level workflow graphs, outperforming the strongest baseline by 3-5 points on OOD benchmarks
ToolLIFT abstracts tool trajectories into function-level workflow graphs, lifting OOD accuracy by 4+ points on average; HyperAgent builds tool-schema hypergraphs with deficit-oriented expansion, beating ReAct by 14.3 points on AppWorld with lower token cost; a multilingual multi-agent planning diagnosis finds that planning grounding failures rise with decreasing language resources, and the TART fix improves scores by 5.6 points on average