overfeed.news

Tópico

Agentes

1.738documentos

214últimos 7 dias

arXiv AI Papers

TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation

Verifier scores now serve as both benchmark metrics and training rewards for large language model (LLM) agents, and a change in score is routinely read as a change in capability. It may instead reflect a change in the evaluation. We introduce TRACE, a protocol that turns a score change from a verdict into a testable diagnosis: it applies a targeted change to one part of an evaluation, compares paired runs, checks whether the agent's behavior changed, and rescores unchanged trajectories to test whether the scoring rule is responsible. In a controlled suite of 25 synthetic tasks, renaming tools lowers a scripted agent's score by 0.250 even though it performs exactly the same operations; restoring the original names at scoring time closes the entire gap, while the same mutation exposes a genuine behavioral failure in a second agent. On public τ^2-bench tasks with four LLM agents, an initial 30-task study finds mixed reward changes whose one clear effect does not replicate. In a larger follow-up on 88 new tasks with repeated runs per condition, renaming tools or reformatting tool outputs leaves reward unchanged to within 0.10 for seven of eight agent-change pairs, whereas tool names that deliberately mislead lower every agent's reward by 0.20-0.44, showing that the setup can detect real effects. Identical reruns flip 15-36% of task outcomes, so single-run comparisons cannot separate presentation effects from run-to-run variation. Two frontier LLM judges give consistent verdicts when a fixed trajectory is presented differently, yet disagree with each other on 57% of the same records, largely because one grades procedure rather than outcome. TRACE thus separates what a score change says about the agent from what it says about the measurement.

en
arXiv AI Papers

Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games

Deep reinforcement learning agents reach strong performance in real-time strategy games but can be brittle against opponents outside their training distribution. Separating strategic command selection from learned unit control allows different strategies to be selected for different opponents while reusing the same execution policy. This requires an executor that can follow different commands and measurable criteria for assessing whether it does so. We introduce a constrained command-conditioned Proximal Policy Optimization (PPO) policy, the executor, for MicroRTS, a real-time strategy environment. Discrete commands specify strategic objectives and behavioral requirements for economy, army composition, military posture, and worker policy over multiple environment steps; the executor determines the unit-level actions used to fulfill them. A Thompson-sampling bandit acts as the strategist, selecting command tuples from an estimate of the opponent's strategy built from in-game observations rather than opponent identity. In a controlled comparison with a flat PPO baseline trained with the same architecture, budget, curriculum and self-play league, the strategist-executor system wins significantly more often against three of the four strongest opponents on a training map, including the two strongest held-out ones (0.55 to 0.97 and 0.01 to 0.34), with no significant difference against the others.

en
arXiv AI Papers

Harness Evolution Hits a Ceiling: When Weight Training Should Begin

Improving a long-horizon LLM agent means evolving the harness around a frozen model or training its weights. We let a self-evolving harness make the system stronger first, then cross seed and evolved harnesses with base and trained weights to learn which gains the trained model keeps and which still need the runtime. We show that the right lever can be read off the agent's failure composition: labelling failed trajectories by the first signal that fires separates process failures (blocked calls, loops, exhausted step budgets) from content failures (a delivered plan that is poor). Harness evolution repairs the former, the behaviour it instils can be trained into the weights, and content failures are what weight training is for. On DeepPlanning, a self-evolving harness loop lifts the held-out score of Qwen3.5-4B from 0.16 to 0.30 and of Qwen3.5-9B from 0.32 to 0.44; for 4B, held-out delivery rises from 55% to 90% while content failures are left for the weights. LoRA adapters trained on evolved-harness trajectories internalise the gain: under the original harness they add +0.13 on held-out tasks for both sizes; on 4B they stack with the harness to more than double the held-out score, and on 9B the adapter alone matches the full evolution line, cutting content failures from a quarter of trajectories to one in twenty. A placebo adapter trained on answer-shuffled trajectories falls below the base model. The loop transfers to WebArena-Lite (+0.09 on 117 unseen tasks), where the gain lives in what the model sees and adapters do not add to it. The result is a diagnose-then-intervene rule applied twice: read the failure composition to choose between harness and weights, then read what the accepted edits changed to decide which gains to train in. Scores are four-rollout means against fresh anchors, same-night except where marked, across eight models from six families and two benchmarks.

en
arXiv AI Papers

Evidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs

Automated interviewers and conversational agents are increasingly used in research, recruitment, customer service, and education. However, many existing systems rely on fixed question sequences and provide limited context-based personalization without considering participants' knowledge, which can lead to repetitive or irrelevant follow-up questions. Therefore, there is a need for an adaptive interviewing system that can adjust question depth while maintaining conversational continuity and semantic progression. To address this, an Evidence-Traceable Dynamic Interviewer Architecture is presented using a locally hosted Large Language Model (LLM), with the interview continuously adapted throughout the entire conversation based on the participant's responses and evolving context. The interviewer profiles participants' expertise in real time to generate knowledge-appropriate questions, well-articulated responses, and smooth transition messages that support conversational continuity. A five-module prompt-driven architecture and persistent interview-state record support these functions. The interviewer was evaluated with 246 participants. Expertise Profiling module (M3) showed 78.9% exact agreement with independently reported participant expertise, with a weighted Cohen's K of 0.80. Generate Iterative Questions module (M4) showed a strong expertise-complexity association (p=.79, p<.001), and participants reported high relevance (mean 4.41), engagement (mean 4.32), and satisfaction (mean 4.38), providing evidence that the architecture's adaptive components operated consistently with their intended functions while participants reported a positive interview experience.

en
arXiv AI Papers

SkillContrast: Difference-Guided Text Selection for Agent Skill Reranking

Similar agent skills can share instructions but differ in their conditions of use. Query-based text selection may retain shared instructions and omit these distinctions. We introduce SkillContrast, a training-free selector that compares retrieved skills and retains their differing text with local context for a pretrained reranker. On 1,235 requests from SameCapRisk-Bench, it yields 54-72 more clean hits (requests that retrieve a helpful skill without its marked risky sibling) than TF-IDF query selection at identical per-candidate input lengths, across 2 retrievers and 2 reranker sizes. Length-matched component replacements identify differing text as the main contributor in the primary setting, with smaller, mixed context effects. Relative to full skill bodies, SkillContrast uses 51.1-58.8% fewer model-input tokens, with 10-18 fewer clean hits at 0.6B and matching or higher observed clean-hit counts at 4B. Candidate-relative differences thus complement query relevance in selecting compact reranking inputs.

en
arXiv AI Papers

One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents

Coding agents are extended with agent skills, directories whose SKILL.md tells the model when and how to perform a task. Because skills come from independent sources (teams, developers, plugins, copied collections), an installed skill can be co-installed with a similar skill doing the same job, and the model picks between them by name and description alone. In a conflict, the installed skill loses core functions (e.g., a ban on touching git) because the similar skill runs instead or changes what it does. The task still passes, so benchmarks that check only task completion miss such cases. We present the first empirical study of such conflicts. From snapshots of 20,947 repositories, we mine 822,109 candidate similar-skill pairs, have an LLM judge a stratified sample of 3,754, and run 312 confirmed pairs on three models (6,368 runs, 169,294 tool calls, 542 agent-hours). We report five findings. (1) Conflict-prone skills are common: nearly one in four installed skills is co-installed with one that does the same job, and 37% of judged skills sit inside copied collections. (2) Most such pairs involve normative skills, then capability skills. (3) Without lowering task completion, a similar skill takes one in five runs from the installed skill, and runs that open the similar skill first lose over a third of the exclusive core functions that only the installed skill fulfills. (4) Install location decides which skill runs, listing order barely matters, and the final reply names the skill used in only 0.9% of substituted runs. (5) Conflicts are decided at the first skill read, almost always before any file is changed, and a pre-tool hook at that read restores fidelity on exclusive core functions to the level of runs that open the installed skill first. Benchmarks should thus score exclusive core functions, and platforms should guard the first read and show which skill ran.

en
arXiv AI Papers

AgentEvolver: System-Wide Self-Evolution Through Task Execution

An agent can complete a task without improving how it works. Turning task experience into reusable capability requires connecting the changed component to its evaluation and subsequent use. We present AgentEvolver, a system for developing capabilities during task execution while keeping the foundation model fixed. Eight entity families expose reusable operations, methods, agents, control flow, interfaces, and supporting state to revision through a common versioned lifecycle. A shared Runtime coordinates ongoing work, while persistent planning and recoverable context preserve task direction and supporting evidence. We evaluate task outcomes on SWE-bench Pro Public and examine capability changes in six application cases. The team reports an 82.08\% resolution rate with evolution, exceeding its reported baseline without evolution. The cases show retained capabilities entering later website, game, and research work, while also documenting incomplete objectives and an unsuccessful strategy. These findings distinguish improvement in a reusable component from success on the final task. AgentEvolver provides a concrete basis for studying capability accumulation through execution; independent-task transfer and total development cost remain open questions.

en
arXiv AI Papers

Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems

LLM-based multi-agent systems (MASs) are increasingly used to solve complex tasks through coordinated reasoning, tool use, and interaction with external resources. However, attributing failures in such systems remains challenging because the observed outcome often does not directly reveal the error responsible for the failed execution. In this work, the attribution target is the decisive error, defined as the agent--step pair whose correction would recover the failed execution. Existing approaches largely identify suspicious steps without explicitly modeling how errors propagate across interactions or persist in unresolved loops, making decisive errors difficult to distinguish from downstream failure symptoms. We propose Error-Propagation Modeling for Failure Attribution (EMFA). EMFA constructs a structured representation of the failed trajectory, models both cascading propagation and persistent interaction loops, and uses propagation-aware candidate screening followed by counterfactual verification to identify the decisive agent--step pair. On the Who\&When benchmark, EMFA achieves state-of-the-art step-level attribution accuracy and remains competitive at the agent level. It improves the previous best step-level results by 3.45 and 4.40 percentage points on the Hand-Crafted and Algorithm-Generated subsets, respectively.

en
arXiv AI Papers

Runnable Commit Untangling for Coding Agents

Coding agents produce large, tangled patches that mix multiple development purposes, making the code hard to review and maintain. Commit untangling offers the promise of organizing such large patches into untangled, manageable commits. This paper emphasizes two important limitations in existing commit untangling studies. First, they do not consider that untangled commits are ordered and should leave the code runnable. In practice, maintainers are unlikely to accept commits that prevent the code from running. Second, existing studies claim that commit untangling helps software maintenance. However, they conduct syntactic comparisons between the untangled commits and developers' original commits without directly showing the claimed maintenance benefits. To address these gaps, this paper makes two novel contributions: (1) RucTangle, the first agentic method that untangles commits while keeping the code runnable after each commit; and (2) TangleEval, the first evaluation framework that quantifies how untangled, manageable commit histories help coding agents repair bugs. We compare RucTangle against four untangling methods on 131 agent-generated patches. All histories produced by RucTangle are runnable, while baselines produce 20.6%-37.4% unrunnable commit histories. We further collect 453 agent-generated patches that introduce regressions (i.e., causing previously passing tests to fail) and ask two other coding agents to repair regressions. Augmenting agent context with RucTangle-produced histories yields 5.2% absolute improvement in pass@1. We also analyze agent trajectories to learn how they use untangled commits to navigate and fix bugs. Our findings demonstrate the value of adopting established software engineering practices in the era of coding agents, which broaden the future research agenda: how can agents actively use software history to make better development decisions?

en
arXiv AI Papers

SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving

End-to-end autonomous driving demands trajectory planners that are both highly accurate and cheap enough for edge deployment. State-of-the-art artificial neural network (ANN) planners meet the accuracy requirement at the cost of heavy dense computation, while spiking neural networks (SNNs)---though promising orders-of-magnitude energy savings through sparse, event-driven arithmetic---still lag far behind in planning accuracy. We present SDPAD, a fully spike-driven end-to-end planning pipeline that closes this gap. SDPAD converts a pre-trained ANN perception stack into integer-spike form via quantized ANN2SNN conversion, lifts multi-view images into the bird's-eye-view (BEV) space with a spike-driven-max (SDM) depth distribution (Spike-3D-Lift), and plans through the Spike-QFormer, a spiking query transformer in which ego, agent, and map queries distilled from the BEV scene are fused by learnable waypoint queries via cross-attention, followed by deformable spike-cross-attention refinement. Every operation is gated by integer spikes and inference is a single feed-forward pass without temporal simulation loops. On the nuScenes open-loop benchmark, SDPAD achieves an average L_2 error of 0.40\,m and a collision rate of 0.12\%, on par with strong ANN planners while consuming 69.9\,mJ---less than 2\% of recent ANN baselines. In closed-loop evaluation on the NAVSIM navtest split, SDPAD reaches 86.3 PDMS, surpassing the previous SNN planner SAD by 4.3 points and matching mainstream ANN planners at a fraction of their energy. To our knowledge, SDPAD is the first fully spike-driven planner evaluated in end-to-end autonomous driving, demonstrating that SNNs can rival dense ANNs in complex driving tasks.

en
arXiv AI Papers

Chronos Enables Code Agents to Reason over Software Evolution

Historical pull requests record the design decisions, compatibility constraints, and implementation patterns behind a codebase's current state. Experience relevant to a new task can span related changes whose descriptions emphasize different concerns. We introduce Chronos, a test-time framework that makes this connected history available to large language model (LLM)-based code agents. Chronos distills merged pull requests into structured experience cards and connects them through a typed graph of code-level, developer-intent, and organizational relations. Semantic search identifies entry cards, and weighted multi-hop expansion retrieves connected changes for selective reading. The same memory guides candidate generation and patch selection: a patch-focused change agent and a validation-strategy agent each develop a patch, and an evolution steward consults history to select between them. On SWE-Bench Verified, the full workflow improves SWE-Agent across all six evaluated LLM backbones, raising the mean resolution rate from 69.2% to 72.9% and reaching 79.8% with MiniMax M2.5. With the same backbone, it raises resolution rates from 48.3% to 51.7% on SWE-Bench Pro and from 41.0% to 43.5% on FEA-Bench Lite. Both experience-guided single-agent variants also outperform the base agent. In a human evaluation on 100 tasks with ten cards retrieved per task, graph-grounded retrieval increases the mean number of useful cards from 1.24 to 2.87 over flat semantic retrieval. These results demonstrate the value of PR relations for retrieving useful repository experience and of the evaluated workflows for applying that experience during patch generation and selection.

en
arXiv AI Papers

Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies

The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently. Despite great success achieved, existing retrieval-based memory approaches typically overlook the differences between memories and employ a unified strategy to process all memories, leading to suboptimal performance. Thus, an intuitive question arises: can we categorize memory into different types and select appropriate strategies? However, given the topic-rich, scenario-complex, and boundary-blurred nature of memory scenarios, achieving precise classification of memories is not easy. To address this challenge, we propose a memory multi-class dataset in this paper, termed TriMEM, which provides precise annotations for memory types across diverse scenarios. Building upon this foundation, we propose a novel memory framework, named MemoType, which can adaptively recognize each memory and query type with the learned router model. With the memory and query routing, MemoType can retrieve the memory with corresponding query types and design tailored retrieval strategies, thereby enhancing the retrieval performance. Moreover, we theoretically prove that any single retrieval strategy is subject to a fundamental upper bound on its expected retrieval precision in multi-class corpora, leading to systematic precision degradation. Extensive experiments on three datasets demonstrate that MemoType consistently outperforms existing methods, achieving up to 16.18% improvement in Recall@1.

en
AWS Machine Learning Blog

Introducing Claude Haiku 5.5 on AWS

Claude Haiku 5.5 is now available on Amazon Bedrock and Claude Platform on AWS. According to Anthropic, it is the fastest, most efficient model in the Claude 5.5 family, built for subagents and high-volume, cost-sensitive work, and costs around 75% less than Claude Haiku 4.5 for most tasks. This post covers its improvements and how to get started.

en
Agentes — overfeed.news